The coffee tasted like ash. Brian grimaced and tossed the half-finished cup into the trash. The email had ruined his morning. He felt a tremor run through him, a physical manifestation of his unease. He felt trapped, cornered.

He opened the announcement again, scrolling through the dense text. He felt his face flush. He was scheduled to present at the next client meeting, but his enthusiasm, his confidence, had evaporated.

He slammed his laptop shut, the sound sharp and defiant. He needed to regroup, to find some semblance of control in this spiraling situation.

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