Year: 2025
Type: conference-paper
Abstract: Large language models (LLMs) show promising capabilities in predicting human emotions from text.However, the mechanisms through which these models process emotional stimuli remain largely unexplored.Our study addresses this gap by investigating how autoregressive LLMs infer emotions, showing that emotion representations are functionally localized to specific regions in the model.Our evaluation includes diverse model families and sizes, and is supported by robustness checks.We then show that the identified representations are psychologically plausible by drawing on cognitive appraisal theory-a well-established psychological framework positing that emotions emerge from evaluations (appraisals) of environmental stimuli.By causally intervening on construed appraisal concepts, we steer the generation and show that the outputs align with theoretical and intuitive expectations.This work highlights a novel way to causally intervene and control emotion inference, potentially benefiting safety and alignment in sensitive affective domains.Code at: GitHub repo.# Prompt Template 1 What are the inferred emotions in the following contexts?Context: My first child was born.Answer: joy Context: My dog died last week.Answer: sadness
Language: English
Topic: Emotion and Mood Recognition
Subfield: Experimental and Cognitive Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: gold
Funder: Army Research Office
Award: G7452299184
OpenAlex ID: W4412888258