“Condos? Are you kidding me?” David slammed the door to his apartment so hard the picture frames on the wall rattled. His face was flushed, his jaw tight. He hated this. Hated the thought of leaving. He ran his hand through his hair, dislodging a few strands.

He found himself pacing the length of his living room, his steps heavy on the hardwood floor. He felt a throbbing sensation in his temples. He visualized the changes: the new owners, the renovations, the inevitable feeling of being an outsider in his own home. He remembered the many nights spent in this apartment, and it felt like it was all being ripped away from him.

He picked up a book and tossed it across the room. He didn’t want to read; he wanted to scream. He knew this would be a fight.

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