David slammed his fist on the table, making the coffee cup jump. He let out a frustrated growl. The article, the project he had dedicated months to, was published. And someone else was taking credit. His shoulders slumped, the weight of disappointment crushing him.

He pushed away from his desk. The chair scraped across the floor with a sound that grated on his nerves. He needed air. He walked to the window, the fresh air offering no comfort. He felt lost, adrift in a sea of resentment.

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