Emotion Representation in Language Models

Ask about this topic

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

64 papers9 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

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

    Oct 27, 2026Iwan WilliamsEmotion Representation in Language ModelsLLM Evaluation

    University of Copenhagen, Center for Philosophy of Artificial Intelligence, Section for Philosophy, Department of Communication

  2. The Geometry of Emotion Representations Across Scale, Depth, and Instruction Tuning

    Oct 26, 2026Adam HollowellEmotion Representation in Language ModelsRepresentation Geometry in Language Models

    University of North Carolina at Chapel Hill

  3. From Encoding to Generation: Towards Empathetic Large Language Models

    Oct 20, 2026Samhita Bollepally, Takashi Yamauchi, Marissa WestEmotion Representation in Language ModelsEmotion-Aware Dialogue Generation

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

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

    Columbia University

  5. 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

    Nagoya University, Nagoya, Aichi, Japan · National Institute of Informatics, Tokyo, Japan

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

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

    INSAIT, Sofia University “St. Kliment Ohridski” · University of British Columbia

  7. Steering Follows Geometry, Not Labels: Emotion Directions in a Full-Duplex Speech Model

    Oct 6, 2026Pulak KuliControllable Speech GenerationSpeech Language Models

    Independent Researcher

  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

    Department of Computer Science, William & Mary, Williamsburg, USA

  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

    Department of Computer Science, William & Mary, Williamsburg, VA, USA

  10. EMODE: Dynamic Para-Semantic Experts for Emotion-Aware Speech Language Modeling

    Oct 3, 2026Jianan Pan, Yiwen Gu, Xinze Li +2Speech Language ModelsEmotion Representation in Language Models

    Zhejiang University Hangzhou, China

  11. Language Models Act on Hidden Valence

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

    Reciprocal Research · University of Warwick

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

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

    Department of Computer Science and Engineering Islamic University of Technology, Dhaka, Bangladesh

  13. 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

    Idiap Research Institute, Switzerland · EPFL, Switzerland · Uniphore, USA & India +1

  14. 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

    Ruhr-University Bochum · Reciprocal Research

  15. 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

    Department of Artificial Intelligence, Ajou University

  16. 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

    Department of Computer Software Hanyang University, Seoul

  17. 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

    Faculty of Computer and Information Science, University of Haifa, Israel · School of Therapy, Counseling and Human Development, University of Haifa, Israel · The PhD Program of Hermeneutics and Culture, Interdisciplinary Studies Unit, Bar-Ilan University, Israel +1

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

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

    Department of Psychiatry & Behavioral Sciences, Stanford University School of Medicine, Stanford, CA, USA · Wu Tsai Neurosciences Institute, Stanford University, Stanford, CA, USA · Kaiser Permanente, San Jose, CA, USA +2

  19. 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

    1Université Sorbonne Paris Nord, CNRS, Laboratoire d’Informatique de Paris Nord, LIPN · 2LORIA, CNRS, Université de Lorraine

  20. Replicating the Geometry of Emotion Representations in a Base Open-Weights Model

    Sep 1, 2026Adam HollowellEmotion Representation in Language ModelsRepresentation Geometry in Language Models

    University of North Carolina at Chapel Hill

  21. Controllable Affective Generation via Latent Vector Steering

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

    Gaoling School of Artificial Intelligence, Renmin University of China · Tencent Jarvis Lab · Beijing Key Laboratory of Research on Large Models and Intelligent Governance +1

  22. Multilingual Emotion Neurons in Large Audio-Language Models

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

    Center for Language and Speech Processing (CLSP), Johns Hopkins University, USA · Group on Language, Audio & Music (GLAM), Imperial College London, UK

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

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

    Bruno Kessler Foundation

  24. VIBE: A VAD-Informed Benchmark for Entity-Centered Affective Profiling of Large Language Model Outputs

    Aug 4, 2026Andrei Chetvergov, Alexander Evseev, Timofei Sivoraksha +4LLM EvaluationLanguage Model Bias Evaluation

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

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

    Institute for the Brain and Cognitive Sciences, University of Connecticut, Storrs, CT 06269, USA · Department of Linguistics, The University of Texas at Austin, Austin, TX 78712, USA

  26. Adaptive Emotional Video Captioning via Affective Heterogeneous Graph Reasoning and Multi-task Joint Learning

    Jul 31, 2026Junbo Wang, Liangyu Fu, Yuke Li +2Video CaptioningEmotion Representation in Language Models

    School of Software, Northwestern Polytechnical University, Xi’an 710129, China · School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710049, China · School of Computer Science, The University of Sydney, NSW 2006, Australia

  27. How Affect Propagates among LLM Agents: Emergent Emotional Contagion in Crowd Simulation

    Jul 27, 2026Funda DurupinarHuman Behavior SimulationAgent-Based Modeling

    Computer Science Department University of Massachusetts Boston, MA 02125

  28. EmoTrace: An Emotion Trajectory-Centered Framework for Psychological Support Dialogue Generation

    Jul 26, 2026Kaitong Weng, Lixin Liu, Zihao Liu +2Mental Health CounselingEmotional Support Conversation

    Shenzhen International Graduate School, Tsinghua University

  29. REGARD: Regional Affective Differences in Large Language Models

    Jul 22, 2026Andrei Chetvergov, Alexander Evseev, Mikhail Solovev +5Political Bias in Language ModelsValence-Arousal Modeling

    Ivannikov Institute for System Programming of the Russian Academy of Sciences, Moscow, Russia · Russian Presidential Academy of National Economy and Public Administration, Moscow, Russia

  30. Semantic Primes as Explanans for Emotion in Large Language Models

    Jul 21, 2026Frank XingLLM InterpretabilityMechanistic Interpretability

    University of Reading