Why Are Some Emotions Harder for LLMs? Uncovering the Causal Mechanisms of Emotion Inference via Sparse Autoencoders

arXiv:2604.25866 · cs.CL · Submitted 2026-04-28 · Read on arXiv

cs.CL

Submitted: 2026-04-28

Updated: 2026-10-24

Terminology

• Steering — 2× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Language Models (LLMs) — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 9 episodes
• Mechanistic Interpretability — 1× in this paper · explained in 4 episodes
• Sparse Autoencoders (SAEs) — 1× in this paper · explained in 4 episodes

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering