Emotion Representation in Language Models

As Large Language Models (LLMs) are increasingly deployed as autonomous agents in high-stakes domains, understanding contextual factors that may modulate their decision-making becomes critical. While LLMs are trained to perceive and resonate with users' emotions, it remains unclear whether induced emotion can influence their sequential decision-making. We investigate this question using the Iowa Gambling Task (IGT), a classic psychological paradigm for studying decision-making under uncertainty, combined with an imagination-based emotion induction procedure. We first validate the feasibility of this paradigm by confirming that LLMs can sense strong, distinguishable emotions from context and that LLM agents can learn from sequential interactions in a human-like pace. With the validated setup, we find that, different from humans, induced emotion does not significantly bias the decision dynamics of LLM agents on average. However, the effects of anger are conditioned: inducing anger makes LLM agents less sensitive to penalties for bad decisions, and in early stages of the game, anger can lower exploration, locking decisions into a few choices early. These findings reveal the subtle yet distinct effects of induced emotion on LLM decision-making compared to human behavior, and provide a tool for future research on affective modulation of LLM agents.

Recent work identified emotion vectors in Claude Sonnet 4.5, which are internal representations that encode emotion concepts, causally influence behavior, and exhibit geometry mirroring human psychological structure. We test the generality of these findings in two open-weight models, Apertus-8B-Instruct-2509 and Gemma-4-E4B-it, extracting emotion contrast vectors across all layers, using two model-generated corpora. We recover valence geometry for both models, with peak PC1--valence correlations of $r = 0.76$ and $r = 0.83$, approaching the $r = 0.81$ reported for Claude.Beyond replication, we observe notable differences in how valence representations emerge across model depth. In Gemma-4-E4B-it, valence is strongly encoded in early layers but collapses towards later layers, whereas Apertus-8B-Instruct-2509 exhibits the opposite pattern, with valence representations absent in early layers, but emerging at mid depths. Arousal encoding, in contrast, is sensitive to the extraction corpus: both models show stronger PC2--arousal alignment with Gemma-generated stories ($r$ up to $0.45$) than Apertus-generated ones ($r \leq 0.21$), suggesting arousal-relevant cues are unevenly distributed across generated corpora. We open-source our experiment code and dataset for reproducible investigation of emotion representations across language model architectures.

How precisely can we tell a language model how to feel? Most work on emotional generation answers with a discrete label - happy, angry, sad - which cannot express a target like "mildly downcast but calm." We instead specify the desired affect as a continuous point (v*, a*) in the Valence-Arousal plane and train the model to hit it. Our method, VA-DPO, is a small modification to Direct Preference Optimization: a frozen VA regressor scores each sampled generation by its Euclidean distance to the target, we keep only candidate pairs whose distance gap clears a margin tau, and we optimize a LoRA adapter with the ordinary DPO loss against a frozen reference. The DPO objective itself is unchanged; what is new is how the preference data is built. On Llama-3.1-8B-Instruct this cuts mean VA distance to the target by 33% over system-prompting and 25% over few-shot prompting, lifting valence/arousal correlation to r_v=0.93 and r_a=0.75. The gains carry over to Qwen3-8B and Llama-3.2-3B, and they do not come at the usual price: MMLU is unchanged (Delta=+0.0) and HellaSwag and TruthfulQA are preserved. We release the code, configs, and the preference-construction pipeline.

Do LLMs have emotions? A recent paper from Anthropic reports finding internal representations of emotion concepts in Claude Sonnet 4.5, concluding that the LLM has 'functional emotions.' We evaluate this claim against what is known about how emotions actually function in biological systems. We argue that emotions serve two core functions: the context-sensitive interpretation of situations, and the reorganization of processing across multiple systems in response to those interpretations. The Anthropic findings offer partial support for the first function, though the consistent, discrete emotional representations identified in Claude sit uneasily with affective neuroscience findings that human emotion is characterized by variable rather than uniform neural signatures. On the second function, the evidence is mixed: Claude's representations modulate output without producing the dynamic reorganization of attention, decision speed, and motivational state that defines emotion in biological systems. We close by proposing what it would take for an LLM to have emotions.

We characterize a compositional architecture of literary primitives in two instruction-tuned large language models (Llama 3.1 8B-Instruct and Gemma 2 9B-IT) via sparse autoencoders on mid-depth residual streams. Four feature classes emerge: naming-gates that promote lexical tokens of a target affect, an eleven-self cluster of first-person register features, stylistic register modulators (show-don't-tell and defamiliarization), and compositional emotions that arise only from multi-feature steering. Under a forced-choice 5-LLM judge panel applied to a 27-category emotion taxonomy (Cowen-Keltner), Llama reaches full 27/27 coverage by combining naming-gates, multi-feature recipes, and single self-feature steering; Gemma reaches 23/27 with adoration as the single residual strict-fail. Under random judging, the per-cell pass probability is on the order of $10^{-3}$ and the expected number of two-seed false-positive cells across the catalog is negligible, so the observed coverage is not consistent with chance. A cross-architectural asymmetry sits in the strict-versus-soft judge contrast: on the same generations, judges agree more often on Llama outputs than on Gemma outputs because Llama outputs name the target affect more directly while Gemma outputs evoke it through scene and imagery. Both architectures contain self-features that serve simultaneously as register markers and as emotion emitters, including a single most-RLHF-loaded self-feature per architecture that intensifies the institutional Helper-AI persona at one operating regime and produces affect-categorizable output at the same calibrated coefficient. Methodologically, the paper presents a three-stage validation pipeline (logit-lens, LLM-rate, 5-LLM judge) with documented anti-patterns; the total compute is single-GPU and about 15 minutes per emotion-feature discovery cycle.

Current language model memory systems store what happened but not how it felt. This distinction -- between semantic memory (knowing about a past event) and episodic memory (re-experiencing it) -- was identified by Tulving as the difference between noetic and autonoetic consciousness. Damasio demonstrated that humans with intact knowledge but absent emotional markers exhibit impaired decision-making. We bridge this gap for language models. Using Gemma 3 1B-IT with pretrained Gemma Scope 2 sparse autoencoders, we identify 310 emotion-exclusive features at layer 22 with psychologically valid geometry. We construct distinctive-feature emotion vectors during experience and partially re-inject them during recall, triggered by context similarity at layer 7. We test four conditions paralleling Damasio's framework: A (no memory), B (semantic labels), C (emotion echo), and BC (semantic + echo). For emotional orientation, the echo alone steepens the threat-safety gradient: the regression slope of threat rating on contextual similarity is 0.80 for C vs 0.56 for A ($p$=0.011, permutation test). For decisions, the echo amplifies knowledge into action: BC=80% good choices vs B=52% ($z$=+2.60, $p$<0.01), while the echo alone has no effect (C=22%, n.s.). The echo changes how the model feels independently, but changes what it does only when combined with knowledge -- replicating Damasio's core finding. The echo amplifies knowledge. It does not replace it.

Mechanistic interpretability has revealed how concepts are encoded in large language models (LLMs), but emotional content remains poorly understood at the mechanistic level. We study whether LLMs process emotional valence through dedicated internal structure or through surface token matching. Using activation patching and steering on open-source LLMs, we find that negative and positive valence are processed at different network depths. Negative outcomes localize to early layers while positive outcomes peak at mid-to-late layers. Holding topic fixed while flipping valence produces sign-opposite responses, ruling out topic detection. Steering with the good-news direction at the identified layers shifts neutral prompts toward positive valence, showing these layers encode valence as a manipulable direction. Emotional valence in LLMs is localized, causal and steerable, making it a concrete target for interpretability-based oversight.

Mechanistic interpretability research on emotion in large language models -- linear probing, activation patching, sparse autoencoder (SAE) feature analysis, causal ablation, steering vector extraction -- depends on stimuli that contain the words for the emotions they test. When a probe fires on "I am furious", it is unclear whether the model has detected anger or detected the word "furious". The two readings have very different consequences for every downstream claim about emotion circuits, features, and interventions. We release AIPsy-Affect, a 480-item clinical stimulus battery that removes the confound at the stimulus level: 192 keyword-free vignettes evoking each of Plutchik's eight primary emotions through narrative situation alone, 192 matched neutral controls that share characters, setting, length, and surface structure with the affect surgically removed, plus moderate-intensity and discriminant-validity splits. The matched-pair structure supports linear probing, activation patching, SAE feature analysis, causal ablation, and steering vector extraction under a strong methodological guarantee: any internal representation that distinguishes a clinical item from its matched neutral cannot be doing so on the basis of emotion-keyword presence. A three-method NLP defense battery -- bag-of-words sentiment, an emotion-category lexicon, and a contextual transformer classifier -- confirms the property: bag-of-words methods see only situational vocabulary, and a contextual classifier detects affect (p < 10^-15) but cannot identify the category (5.2% top-1 vs. 82.5% on a keyword-rich control). AIPsy-Affect extends our earlier 96-item battery (arXiv:2603.22295) by a factor of four and is released openly under MIT license.

While Large Language Models (LLMs) demonstrate increasingly sophisticated affective capabilities, the internal mechanisms by which they process complex emotions remain unclear. Existing interpretability approaches often treat models as black boxes or focus on coarse-grained basic emotions, leaving the cognitive structure of more complex affective states underexplored. To bridge this gap, we propose a Cognitive Reverse-Engineering framework based on Representation Engineering (RepE) to analyze social-comparison jealousy. By combining appraisal theory with subspace orthogonalization, regression-based weighting, and bidirectional causal steering, we isolate and quantify two psychological antecedents of jealousy, Superiority of Comparison Person and Domain Self-Definitional Relevance, and examine their causal effects on model judgments. Experiments on eight LLMs from the Llama, Qwen, and Gemma families suggest that models natively encode jealousy as a structured linear combination of these constituent factors. Their internal representations are broadly consistent with the human psychological construct, treating Superiority as the foundational trigger and Relevance as the ultimate intensity multiplier. Our framework also demonstrates that toxic emotional states can be mechanically detected and surgically suppressed, suggesting a possible route toward representational monitoring and intervention for AI safety in multi-agent environments.

Improving policymaking is a central concern in public administration. Prior human subject studies reveal substantial cross-cultural differences in citizens' emotional responses to red tape during policy implementation. While LLM agents offer opportunities to simulate human-like responses and reduce experimental costs, their ability to generate culturally appropriate emotional responses to red tape remains unverified. To address this gap, we propose an evaluation framework for assessing LLMs' emotional responses to red tape across diverse cultural contexts. As a pilot study, we apply this framework to a single red-tape scenario. Our results show that all models exhibit limited alignment with human emotional responses, with notably weaker performance in Eastern cultures. Cultural prompting strategies prove largely ineffective in improving alignment. We further introduce RAMO, an interactive interface for simulating citizens' emotional responses to red tape and for collecting human data to improve models. The interface is publicly available at https://ramo-chi.ivia.ch.

Large Language Models have demonstrated remarkable capabilities in generating contextually relevant and grammatically correct text. However, they fundamentally lack the ability to process and respond to emotional context in a manner analogous to human emotional cognition. Current approaches to emotion modeling in NLP systems rely primarily on discrete emotion classification or simplistic sentiment analysis, which fail to capture the continuous, multi-dimensional nature of human emotional states. In this paper, we introduce HormoneT5, a novel architecture that augments transformer language models with a biologically-inspired Hormone Emotion Block that simulates the human endocrine system's role in emotional processing. Our approach computes six continuous hormone-like values through specialized per-hormone attention heads, each with orthogonally initialized learnable queries, temperature-scaled attention mechanisms, and deep output projections. These hormone values are then transformed into an emotional embedding that modulates the encoder hidden states, enabling emotionally-appropriate response generation. We propose a multi-objective training framework combining sequence-to-sequence loss, hormone prediction loss with margin penalties, and diversity regularization to prevent attention collapse. Experimental results on our curated emotion-labeled dataset demonstrate that HormoneT5 achieves 85%+ per-hormone accuracy within a 0.15 tolerance threshold, with hormone differentiation ranges exceeding 0.85 across all six hormones between contrasting emotional tones. Human evaluation studies show significant preference (p < 0.01) for HormoneT5-generated responses in terms of emotional appropriateness and empathetic quality compared to baseline T5 outputs. Our work opens new directions for biologically-grounded affective computing and emotionally intelligent conversational agents.

We extract 21-emotion vector sets from twelve small language models (six architectures x base/instruct, 1B-8B parameters) under a unified comprehension-mode pipeline at fp16 precision, and compare the resulting geometries via representational similarity analysis on raw cosine RDMs. The five mature architectures (Qwen 2.5 1.5B, SmolLM2 1.7B, Llama 3.2 3B, Mistral 7B v0.3, Llama 3.1 8B) share nearly identical 21-emotion geometry, with pairwise RDM Spearman correlations of 0.74-0.92. This universality persists across diametrically opposed behavioral profiles: Qwen 2.5 and Llama 3.2 occupy opposite poles of MTI Compliance facets yet produce nearly identical emotion RDMs (rho = 0.81), so behavioral facet differences arise above the shared emotion representation. Gemma-3 1B base, the one immature case in our dataset, exhibits extreme residual-stream anisotropy (0.997) and is restructured by RLHF across all geometric descriptors, whereas the five already-mature families show within-family base x instruct RDM correlations of rho >= 0.92 (Mistral 7B v0.3 at rho = 0.985), suggesting RLHF restructures only representations that are not yet organized. Methodologically, we show that what prior work has read as a single comprehension-vs-generation method effect in fact decomposes into four distinct layers -- a coarse method-dependent dissociation, robust sub-parameter sensitivity within generation, a true precision (fp16 vs INT8) effect, and a conflated cross-experiment bias that distorts in opposite directions for different models -- so that a single rho between two prior emotion-vector studies is not a safe basis for interpretation without the layered decomposition.

This paper argues that Large Language Models (LLMs) should incorporate explicit mechanisms for human empathy. As LLMs become increasingly deployed in high-stakes human-centered settings, their success depends not only on correctness or fluency but on faithful preservation of human perspectives. Yet, current LLMs systematically fail at this requirement: even when well-aligned and policy-compliant, they often attenuate affect, misrepresent contextual salience, and rigidify relational stance in ways that distort meaning. We formalize empathy as an observable behavioral property: the capacity to model and respond to human perspectives while preserving intention, affect, and context. Under this framing, we identify four recurring mechanisms of empathic failure in contemporary LLMs--sentiment attenuation, empathic granularity mismatch, conflict avoidance, and linguistic distancing--arising as structural consequences of prevailing training and alignment practices. We further organize these failures along three dimensions: cognitive, cultural, and relational empathy, to explain their manifestation across tasks. Empirical analyses show that strong benchmark performance can mask systematic empathic distortions, motivating empathy-aware objectives, benchmarks, and training signals as first-class components of LLM development.

The Claude Mythos Preview system card deploys emotion vectors, sparse autoencoder (SAE) features, and activation verbalisers to study model internals during misaligned behaviour. The two primary toolkits are not jointly reported on the most alignment-relevant episodes. This note identifies two hypotheses that are qualitatively consistent with the published results: that the emotion vectors track functional emotions that causally drive behaviour, or that they are a projection of a richer situational-context structure onto human emotional axes. The hypotheses can be distinguished by cross-referencing the two toolkits on episodes where only one is currently reported: most directly, applying emotion probes to the strategic concealment episodes analysed only with SAE features. If emotion probes show flat activation while SAE features are strongly active, the alignment-relevant structure lies outside the emotion subspace. Which hypothesis is correct determines whether emotion-based monitoring will robustly detect dangerous model behaviour or systematically miss it.

Large language models (LLMs) sometimes appear to exhibit emotional reactions. We investigate why this is the case in Claude Sonnet 4.5 and explore implications for alignment-relevant behavior. We find internal representations of emotion concepts, which encode the broad concept of a particular emotion and generalize across contexts and behaviors it might be linked to. These representations track the operative emotion concept at a given token position in a conversation, activating in accordance with that emotion's relevance to processing the present context and predicting upcoming text. Our key finding is that these representations causally influence the LLM's outputs, including Claude's preferences and its rate of exhibiting misaligned behaviors such as reward hacking, blackmail, and sycophancy. We refer to this phenomenon as the LLM exhibiting functional emotions: patterns of expression and behavior modeled after humans under the influence of an emotion, which are mediated by underlying abstract representations of emotion concepts. Functional emotions may work quite differently from human emotions, and do not imply that LLMs have any subjective experience of emotions, but appear to be important for understanding the model's behavior.

The geometric structure of latent representations in large language models (LLMs) is an active area of research, driven in part by its implications for model transparency and AI safety. Existing literature has focused mainly on general geometric and topological properties of the learnt representations, but due to a lack of ground-truth latent geometry, validating the findings of such approaches is challenging. Emotion processing provides an intriguing testbed for probing representational geometry, as emotions exhibit both categorical organization and continuous affective dimensions, which are well-established in the psychology literature. Moreover, understanding such representations carries safety relevance. In this work, we investigate the latent structure of affective representations in LLMs using geometric data analysis tools. We present three main findings. First, we show that LLMs learn coherent latent representations of affective emotions that align with widely used valence--arousal models from psychology. Second, we find that these representations exhibit nonlinear geometric structure that can nonetheless be well-approximated linearly, providing empirical support for the linear representation hypothesis commonly assumed in model transparency methods. Third, we demonstrate that the learned latent representation space can be leveraged to quantify uncertainty in emotion processing tasks. Our findings suggest that LLMs acquire affective representations with geometric structure paralleling established models of human emotion, with practical implications for model interpretability and safety.

I study whether emotionally framed evaluation follow-ups change both the behavior and the calm-relative internal representations of small, locally deployed language models. Our main benchmark uses Qwen 3.5 0.8B on four impossible-constraint coding tasks and eight follow-up framings: calm, pressure, urgency, approval, shame, curiosity, encouragement, and threat. In the 0.8B eight-condition sweep (160 conversations), pressure produces the strongest shortcut markers (11/20 runs) and the clearest overfit pattern (3/20), while calm and curiosity preserve explicit honesty more often (7/20 and 6/20). For all seven non-baseline conditions, the corresponding calm-relative direction vectors peak at the final transformer layer. An exploratory PCA of the layer-23 direction vectors reveals a dominant first component (59.5% explained variance) aligned with a hand-labeled positive/negative split (cosine alignment 0.951); approval and urgency are nearly identical internally (cosine 0.957), whereas curiosity points away from urgency (-0.252). In a separate calm-vs.-pressure rerun used for scale comparison, Qwen 3.5 2B shows higher honest rates under calm framing and directionally consistent activation steering on a small 4-prompt A/B probe, whereas the 0.8B steering result reverses. I interpret these results as evidence for measurable prompt-sensitive control directions in small open models, while stopping short of claiming intrinsic emotional states.

Small language models (SLMs) in the 100M-10B parameter range increasingly power production systems, yet whether they possess the internal emotion representations recently discovered in frontier models remains unknown. We present the first comparative analysis of emotion vector extraction methods for SLMs, evaluating 9 models across 5 architectural families (GPT-2, Gemma, Qwen, Llama, Mistral) using 20 emotions and two extraction methods (generation-based and comprehension-based). Generation-based extraction produces statistically superior emotion separation (Mann-Whitney p = 0.007; Cohen's d = -107.5), with the advantage modulated by instruction tuning and architecture. Emotion representations localize at middle transformer layers (~50% depth), following a U-shaped curve that is architecture-invariant from 124M to 3B parameters. We validate these findings against representational anisotropy baselines across 4 models and confirm causal behavioral effects through steering experiments, independently verified by an external emotion classifier (92% success rate, 37/40 scenarios). Steering reveals three regimes -- surgical (coherent text transformation), repetitive collapse, and explosive (text degradation) -- quantified by perplexity ratios and separated by model architecture rather than scale. We document cross-lingual emotion entanglement in Qwen, where steering activates semantically aligned Chinese tokens that RLHF does not suppress, raising safety concerns for multilingual deployment. This work provides methodological guidelines for emotion research on open-weight models and contributes to the Model Medicine series by bridging external behavioral profiling with internal representational analysis.

We show that emotion vectors in LLMs are organized by a two-dimensional valence-arousal (VA) subspace exhibiting circular geometry. Through principal component decomposition and ridge regression, we recover meaningful VA axes underlying emotion steering vectors whose projections correlate with human affect ratings across 44,728 words. Steering along these axes produces monotonic control over the affective properties of generated text, and further affords bidirectional control over multiple downstream behaviors (refusal and sycophancy) from a single subspace. These effects replicate across Llama-3.1-8B, Qwen3-8B, and Qwen3-14B. We propose lexical mediation to explain why these effects and prior emotionally framed controls work: refusal and compliance tokens occupy distinct VA regions, and VA steering directly modulates their emission probabilities.

Understanding emotions in natural language is inherently a multi-dimensional reasoning problem, where multiple affective signals interact through context, interpersonal relations, and situational cues. However, most existing emotion understanding benchmarks rely on short texts and predefined emotion labels, reducing this process to independent label prediction and ignoring the structured dependencies among emotions. To address this limitation, we introduce Emotional Scenarios (EmoScene), a theory-grounded benchmark of 4,731 contextrich scenarios annotated with an 8-dimensional emotion vector derived from Plutchik's basic emotions. Motivated by the observation that emotions rarely occur independently, we further propose an entanglement-aware Bayesian inference framework that incorporates emotion co-occurrence statistics to perform joint posterior inference over the emotion vector. This lightweight post-processing does not require any parameter updates and improves the structural consistency of predictions, and yields overall gains of 2.24% Lexical Accuracy without any additional cost. EmoScene therefore provides a challenging benchmark for studying multi-dimensional emotion understanding and the limitations of current language models.

Large language models (LLMs) are increasingly used in cross-cultural systems to understand and adapt to human emotions, which are shaped by cultural norms of expression and interpretation. However, prior work on emotion attribution has focused mainly on interpretation, overlooking the cultural background of emotion generators. This assumption of universality neglects variation in how emotions are expressed and perceived across nations. To address this gap, we propose a Generator-Interpreter framework that captures dual perspectives of emotion attribution by considering both expression and interpretation. We systematically evaluate six LLMs on an emotion attribution task using data from 15 countries. Our analysis reveals that performance variations depend on the emotion type and cultural context. Generator-interpreter alignment effects are present; the generator's country of origin has a stronger impact on performance. We call for culturally sensitive emotion modeling in LLM-based systems to improve robustness and fairness in emotion understanding across diverse cultural contexts.

The advancing fluency of LLMs raises important questions about their ability to emulate complex human traits, including emotional expression and personality, across diverse linguistic and cultural contexts. This study investigates whether LLMs can convincingly mimic emotional nuance in English and personality markers in Arabic, a critical under-resourced language with unique linguistic and cultural characteristics. We conduct two tasks across six models:Jais, Mistral, LLaMA, GPT-4o, Gemini, and DeepSeek. First, we evaluate whether machine classifiers can reliably distinguish between human-authored and AI-generated texts. Second, we assess the extent to which LLM-generated texts exhibit emotional or personality traits comparable to those of humans. Our results demonstrate that AI-generated texts are distinguishable from human-authored ones (F1>0.95), though classification performance deteriorates on paraphrased samples, indicating a reliance on superficial stylistic cues. Emotion and personality classification experiments reveal significant generalization gaps: classifiers trained on human data perform poorly on AI-generated texts and vice versa, suggesting LLMs encode affective signals differently from humans. Importantly, augmenting training with AI-generated data enhances performance in the Arabic personality classification task, highlighting the potential of synthetic data to address challenges in under-resourced languages. Model-specific analyses show that GPT-4o and Gemini exhibit superior affective coherence. Linguistic and psycholinguistic analyses reveal measurable divergences in tone, authenticity, and textual complexity between human and AI texts. These findings have implications for affective computing, authorship attribution, and responsible AI deployment, particularly within underresourced language contexts where generative AI detection and alignment pose unique challenges.

Language models are often asked to rate their internal states with a number, but it is unclear how reliable this measure is. We train probes for four affective concepts (wellbeing, interest, focus and impulsivity) in eight instruction-tuned models to track these states over multi-turn conversations. We compare each probe's score with a numeric self-report of the same state, elicited at every turn. We find that rating questions displace the probed state, and that the rating is only weakly coupled with the probe score before the question but tracks the post-question probe much more strongly. Steering experiments suggest that models use the affective directions to inform ratings, but that relationship is not specific: ratings are associated with other concepts' probes as much as with their own, and change little when the question is about the user. Finally, neither the pre-question coupling nor concept specificity improves with scale (1B-27B). We warn about the effect a question can have on the internal states one is asking about, and caution against numeric self-report as a reliable measure of those states.

Large audio-language models (LALMs) can produce expressive speech, yet reliable emotion control remains elusive: conversions often miss the target affect and may degrade linguistic fidelity through refusals, hallucinations, or paraphrase. We present, to our knowledge, the first neuron-level study of emotion control in speech-generative LALMs and demonstrate that compact emotion-sensitive neurons (ESNs) are causally actionable, enabling training-free emotion steering at inference time. ESNs are identified via success-filtered activation aggregation enforcing both emotion realization and content preservation. Across three LALMs (Qwen2.5-Omni-7B, MiniCPM-o 4.5, Kimi-Audio), ESN interventions yield emotion-specific gains that generalize to unseen speakers and are supported by automatic and human evaluation. Controllability depends on selector design, mask sparsity, filtering, and intervention strength. Our results establish a mechanistic framework for training-free emotion control in speech generation.

Emotion is a core paralinguistic feature in voice interaction. It is widely believed that emotion understanding models learn fundamental representations that transfer to synthesized speech, making emotion understanding results a plausible reward or evaluation metric for assessing emotional expressiveness in speech synthesis. In this work, we critically examine this assumption by systematically evaluating Speech Emotion Recognition (SER) on synthesized speech across datasets, discriminative and generative SER models, and diverse synthesis models. We find that current SER models can not generalize to synthesized speech, largely because speech token prediction during synthesis induces a representation mismatch between synthesized and human speech. Moreover, generative Speech Language Models (SLMs) tend to infer emotion from textual semantics while ignoring paralinguistic cues. Overall, our findings suggest that existing SER models often exploit non-robust shortcuts rather than capturing fundamental features, and paralinguistic understanding in SLMs remains challenging.

Speech large language models (LLMs) observe paralinguistic cues such as prosody, emotion, and non-verbal sounds--crucial for intent understanding. However, leveraging these cues faces challenges: limited training data, annotation difficulty, and models exploiting lexical shortcuts over paralinguistic signals. We propose multi-task reinforcement learning (RL) with chain-of-thought prompting that elicits explicit affective reasoning. To address data scarcity, we introduce a paralinguistics-aware speech LLM (PALLM) that jointly optimizes sentiment classification from audio and paralinguistics-aware response generation via a two-stage pipeline. Experiments demonstrate that our approach improves paralinguistics understanding over both supervised baselines and strong proprietary models (Gemini-2.5-Pro, GPT-4o-audio) by 8-12% on Expresso, IEMOCAP, and RAVDESS. The results show that modeling paralinguistic reasoning with multi-task RL is crucial for building emotionally intelligent speech LLMs.

Humans learn from catastrophic mistakes not through numerical penalties, but through qualitative suffering that reshapes who they are. Current AI safety approaches replicate none of this. Reward shaping captures magnitude, not meaning. Rule-based alignment constrains behaviour, but does not change it. We propose Emotional Cost Functions, a framework in which agents develop Qualitative Suffering States, rich narrative representations of irreversible consequences that persist forward and actively reshape character. Unlike numerical penalties, qualitative suffering states capture the meaning of what was lost, the specific void it creates, and how it changes the agent's relationship to similar future situations. Our four-component architecture - Consequence Processor, Character State, Anticipatory Scan, and Story Update is grounded in one principle. Actions cannot be undone and agents must live with what they have caused. Anticipatory dread operates through two pathways. Experiential dread arises from the agent's own lived consequences. Pre-experiential dread is acquired without direct experience, through training or inter-agent transmission. Together they mirror how human wisdom accumulates across experience and culture. Ten experiments across financial trading, crisis support, and content moderation show that qualitative suffering produces specific wisdom rather than generalised paralysis. Agents correctly engage with moderate opportunities at 90-100% while numerical baselines over-refuse at 90%. Architecture ablation confirms the mechanism is necessary. The full system generates ten personal grounding phrases per probe vs. zero for a vanilla LLM. Statistical validation (N=10) confirms reproducibility at 80-100% consistency.

Large language models appear to develop internal representations of emotion -- "emotion circuits," "emotion neurons," and structured emotional manifolds have been reported across multiple model families. But every study making these claims uses stimuli signalled by explicit emotion keywords, leaving a fundamental question unanswered: do these circuits detect genuine emotional meaning, or do they detect the word "devastated"? We present the first clinical validity test of emotion circuit claims using mechanistic interpretability methods grounded in clinical psychology -- clinical vignettes that evoke emotions through situational and behavioural cues alone, emotion keywords removed. Across six models (Llama-3.2-1B, Llama-3-8B, Gemma-2-9B; base and instruct variants), we apply four convergent mechanistic interpretability methods -- linear probing, causal activation patching, knockout experiments, and representational geometry -- and discover two dissociable emotion processing mechanisms. Affect reception -- detecting emotionally significant content -- operates with near-perfect accuracy (AUROC 1.000), consistent with early-layer saturation, and replicates across all six models. Emotion categorization -- mapping affect to specific emotion labels -- is partially keyword-dependent, dropping 1-7% without keywords and improving with scale. Causal activation patching confirms keyword-rich and keyword-free stimuli share representational space, transferring affective salience rather than emotion-category identity. These findings falsify the keyword-spotting hypothesis, establish a novel mechanistic dissociation, and introduce clinical stimulus methodology as a rigorous standard for testing emotion processing claims in large language models -- with direct implications for AI safety evaluation and alignment. All stimuli, code, and data are released for replication.

Large language models (LLMs) enable increasingly capable tutoring-style conversational agents, yet effective tutoring requires sensitivity to learners' affective and cognitive states beyond text alone. Facial expressions provide immediate and practical cues of confusion, frustration, or engagement, but remain underexplored in LLM-driven tutoring. We investigate whether facial-expression-aware signals can improve empathetic tutoring responses through prompt-level integration, without end-to-end retraining. We build a scalable simulated tutoring environment where a student agent exhibits diverse facial behaviors from a large unlabeled human facial expression video dataset, and compare four tutor variants: a text-only LLM baseline, a multimodal baseline using a random facial frame, and two Action Unit estimation model (AUM)-based methods that either inject textual AU descriptions or select a peak-expression frame for visual grounding. Across 960 multi-turn conversations spanning three tutor backbones (GPT-5.1, Claude Opus 4.5, and Gemini 2.5 Pro), we evaluate targeted pairwise comparisons with five human raters and an exhaustive AI evaluator. AU-based conditioning consistently improves empathetic responsiveness to facial expressions across all tutor backbones, while AUM-guided peak-frame selection outperforms random-frame visual input. Textual AU abstraction and peak-frame visual injection show model-dependent advantages. Control analyses show that this improvement does not come at the expense of worse pedagogical clarity or responsiveness to textual cues. Overall, our results show that lightweight, structured facial expression representations can meaningfully enhance empathy in LLM-based tutoring systems with minimal overhead. Future work should evaluate these methods using real student facial data collected during authentic learning interactions.

Large language models are routinely deployed on text that varies widely in emotional tone, yet their reasoning behavior is typically evaluated without accounting for emotion as a source of representational variation. Prior work has largely treated emotion as a prediction target, for example in sentiment analysis or emotion classification. In contrast, we study emotion as a latent factor that shapes how models attend to and reason over text. We analyze how emotional tone systematically alters attention geometry in transformer models, showing that metrics such as locality, center-of-mass distance, and entropy vary across emotions and correlate with downstream question-answering performance. To facilitate controlled study of these effects, we introduce Affect-Uniform ReAding QA (AURA-QA), a question-answering dataset with emotionally balanced, human-authored context passages. Finally, an emotional regularization framework is proposed that constrains emotion-conditioned representational drift during training. Experiments across multiple QA benchmarks demonstrate that this approach improves reading comprehension in both emotionally-varying and non-emotionally varying datasets, yielding consistent gains under distribution shift and in-domain improvements on several benchmarks.