From across the room, Emily watched the CEO's body language as he delivered the announcement in person, the forced smile and carefully chosen words. She listened to the strained tone in his voice. She’d always admired him, but his words now felt… hollow. Her stomach churned.

She fiddled with her pen, snapping it in half in her hand. The sharp sound surprised her. She felt a constriction in her chest, a physical weight she couldn't explain. She tried to smile at a colleague, but her lips felt stiff, her face frozen.

She wanted to escape. She excused herself, muttering something about a headache, and hurried to the restroom, needing to be alone.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

This story is one of 1,000 stories generated for the emotion upset. 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 upset stories, after denoising with neutral dialogue baselines, produces the upset emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

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

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🤩-0.210