E-STEER Framework Examines Emotion in LLM and Agent Behavior
Mechanistic study on emotion in LLMs via E-STEER.
Existing emotion-aware studies mainly treat emotion as a surface-level style factor or a perception target, the paper states. The work introduces E-STEER for direct representation-level intervention by embedding emotion as a structured variable in hidden states (https://arxiv.org/abs/2604.00005).
The framework examines emotion's impact on objective reasoning, subjective generation, safety, and multi-step agent behaviors. Results indicate non-monotonic emotion-behavior relations (https://arxiv.org/abs/2604.00005).
Specific emotions enhance LLM capability, improve safety, and systematically shape multi-step agent behaviors, consistent with established psychological theories, according to the primary source (https://arxiv.org/abs/2604.00005).
AXIOM: E-STEER shows emotions can be injected at the representation level to steer both capabilities and safety in LLMs and agents.
Sources (1)
- [1]Primary Source(https://arxiv.org/abs/2604.00005)