The silence in the house was almost worse than the constant chatter. David sat at the kitchen table, the half-eaten sandwich in front of him slowly growing stale. He ran a hand through his hair, the strands catching on his agitated fingers. He couldn’t seem to concentrate.

His phone buzzed with a notification, a text from a former colleague, asking about the job hunt. He tossed the phone aside, the screen reflecting the dull grey sky outside. The pressure felt immense, the weight of his parents' unspoken disappointment pressing down on him.

He pushed back from the table, his chair scraping loudly against the linoleum. He needed to get away, to clear his head, to stop feeling this constricting weight. He grabbed his keys and let himself out the back door, the slam echoing through the empty house.

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