Emotion Representation in Language Models

Overview

Researchers study affective representations with probes, geometric analyses, attention inspection, and causal interventions such as activation patching and steering, while also training models to generate or recognize emotion in text and speech. These representations can be structured and can influence outputs, but information that is decodable inside a model is not necessarily used reliably, and does not establish that the model has subjective feelings. Benchmarks increasingly test contextual and keyword-free cues, multidimensional affect, and multilingual and cultural variation, revealing gaps between model outputs, internal signals, and human judgments. Open questions include how robust these representations are, when emotion control improves behavior without harming reliability or safety, and what evidence would distinguish functional emotion processing from human-like emotion.

Latest papers

CardsList

69 papers7 papers in the last four weeks, down 22% on the four weeks before. 0.1% of all new papers.

  1. MemEmo: Evaluating Emotion in Memory Systems

    Nov 16, 2026Peng Liu, Zhen Tao, Jihao Zhao +5Memory-Augmented Language ModelsMemory Agent Benchmarks

  2. Do Language Models Feel the Sentiment? Investigating Emotion Vectors

    Nov 10, 2026Ali Hassan Khan, Saad Bin Ather, Muhammad Saif +2Emotion Representation in Language ModelsLarge Language Model-Based Text Classification

  3. Is your LLM an Agressive Narcissist with Depression? Analyzing Psychological Portraits of Large Language Models

    Nov 2, 2026Polina Fedorinina, Anna Fattakhova, Nadezhda Romanova +2Personality Modeling in Language ModelsBehavioral Consistency of LLM Agents

  4. Do bots feel bad? Assessing empirical evidence for functional valence in LLMs

    Oct 27, 2026Iwan WilliamsEmotion Representation in Language ModelsLLM Evaluation

  5. ToMStories: Interpreting Theory-of-Mind in Synthetic Narratives

    Oct 15, 2026Melanie Subbiah, Chia-En Jacklyn Tsai, Kathleen McKeownTheory of MindImplicit Reasoning in Language Models

  6. Emotion Is Not External Knowledge: Internal Attention Signals for Affective State Reasoning

    Oct 15, 2026Wenqiu Tang, Zhen Wan, Yihui Wang +2Emotion Representation in Language ModelsEmotion Recognition

  7. Empathy Is Not the Scapegoat for Declines in Factuality and Reliability

    Oct 13, 2026Letian Shi, Kanwal Mehreen, Deheng Zhang +1LLM ReliabilityLanguage Model Steering

  8. Tracing a Sparse Emotion-Control Circuit in LLM-Based Text-to-Speech

    Oct 4, 2026Hongfei Du, Jiacheng Shi, Yanfu Zhang +1Mechanistic InterpretabilityControllable Speech Generation

  9. Usage-Modulated Sentiment Representations in Large Language Models

    Oct 4, 2026Hongfei Du, Jiacheng Shi, Yanfu Zhang +2Causal Interventions in Language ModelsRepresentation Geometry in Language Models

  10. Language Models Act on Hidden Valence

    Sep 28, 2026Cameron Berg, Caspar KaiserEmotion Representation in Language Models

  11. Two Emojis of Difference: What Multilingual Affective Generation Benchmarks Actually Measure

    Sep 24, 2026Fardeen Sadab, Adib SakhawatMultilingual Language Model EvaluationLanguage Model Generation Evaluation

  12. From Generative to Discriminative: Lightweight Adaptation of SpeechLLMs for Multimodal Emotion Recognition

    Sep 17, 2026Hasindri Watawana, Sergio Burdisso, Esaú Villatoro-Tello +4Speech Emotion RecognitionSpeech Language Models

  13. The Pain Axis: LLMs Represent Self-Directed Harm and Act on It

    Sep 14, 2026Valen Tagliabue, Leonard Dung, Cameron BergEmotion Representation in Language ModelsLLM Safety

  14. Empathy Is Steerable but Multi-Axial: Mechanism Geometry and Persona Effects in LLMs

    Sep 14, 2026JuHeon Ha, Byounghan Lee, Yunseo Choi +1Language Model SteeringLLM Interpretability

  15. You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs

    Sep 7, 2026Hyunwoo Kim, Usama KhalidDirect Preference OptimizationValence-Arousal Modeling

  16. Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations

    Sep 6, 2026Rotem Dror, Zohar Elyoseph, Yuval Haber +3Large Language Model-Based Role-Play SimulationPersonality Modeling in Language Models

  17. Interpretable Symptom Vectors for Depression in a Large Language Model

    Sep 1, 2026Fangyi Zhu, Ajay Subramanian, Allison Constant +3Depression DetectionRepresentation Geometry in Language Models

  18. Some Emotions Run Deeper: Layer-wise Probing and Causal Intervention in Large Language Models

    Sep 1, 2026Tian Fang, Gaël Guibon, Davide BuscaldiCausal Interventions in Language ModelsEmotion Representation in Language Models

  19. Controllable Affective Generation via Latent Vector Steering

    Aug 26, 2026Xixian Yong, Siyuan Chang, Yingying Zhang +2Controllable Text GenerationActivation Steering

  20. Multilingual Emotion Neurons in Large Audio-Language Models

    Aug 9, 2026Xiutian Zhao, Philipp Koehn, Björn Schuller +1Cross-Lingual Representation AlignmentNeuron-Level Interpretability

  21. Deal Me Maybe: The Role of Emotions in Multi-Agent Negotiation

    Aug 7, 2026Massimiliano Luca, Apoorva Singh, Bruno LepriMulti-Agent NegotiationAutomated Negotiation

  22. Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models

    Aug 3, 2026Linkai Peng, Baorian NuchgedAudio-Language Model EvaluationSpeech Emotion Recognition