Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs
Authors: Sinie van der Ben, Raphaël Baur, Yannick Metz, Mennatallah El-Assady
Organizations: Department of Computer Science, ETH, Zurich, Switzerland.
Abstract
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≤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.
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.
Large language models trained and aligned within different linguistic and regional ecosystems may frame the same political, cultural, and geopolitical entities in different ways. Such differences are often evaluated through sentiment, favorability, or stance, reducing model attitudes to a single positive-negative axis. We introduce REGARD, a study of what drives affective framing differences across LLMs on post-Soviet entities using target-directed Valence-Arousal-Dominance profiling. We query 19 models on 500 region-specific targets, score their responses with two independent LLM judges, GPT-4o-mini and Qwen3.6-35B-A3B, and validate the measurements on a 300-item human-annotated subset. Post-hoc Ward-linkage clustering of all 19 models by affective and response-behavior profiles yields three behavioral clusters that cut across model origin, family, and parameter count. Generic-answer rate is strongly associated with lower arousal (r = -0.81) and with cluster placement: models that deflect evaluative prompts with templated responses cluster together at low arousal regardless of origin. These findings show that VAD profiling captures emotional intensity, a dimension of affective framing that is largely invisible to conventional sentiment-based evaluation.
Andrei Chetvergov, Alexander Evseev, Mikhail Solovev +5