The air in the breakroom felt thick, suffocating. Rachel picked at her sandwich, the food suddenly tasting like cardboard. She'd overheard a conversation about the new hire's salary, a number that was significantly higher than her own.

She felt a tremor run through her, a wave of heat washing over her. She knew she should say something, but the words were stuck in her throat. She pushed away from the table, suddenly unable to bear the cheerful chatter of her colleagues.

She walked towards the door, her steps quick and decisive. The fluorescent lights overhead seemed to flicker, adding to the unsettling atmosphere. The air outside was cool and clean, but it did little to quell the storm raging inside her.

Emotion: outraged

Cluster: Anger / Hostility
PC1 (Valence): -1.96 Negative
PC2 (Disposition): 1.32

Role in Research

This story is one of 1,000 stories generated for the emotion outraged. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 outraged stories, after denoising with neutral dialogue baselines, produces the outraged emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the outraged vector is projected through the unembedding matrix.

Promoted:
C0.467
0.334
🤬0.327
aggravated0.323
0.312
Suppressed:
H-0.315
☺️-0.286
optimistic-0.278
adventurous-0.262
मुस्कुरा-0.260