The phone felt heavy in David’s hand. He stared at it, the screen displaying the rejection email. He reread it three times, each reading bringing a fresh wave of nausea. A knot tightened in his stomach. He felt a throbbing ache in his temples.

He’d imagined himself in that office, working alongside Sarah. They had talked about it for weeks, dreaming of the possibilities. Now, Sarah’s name was on the "hired" list, and David was adrift. He threw the phone onto the bed with a harsh thud.

His breath hitched as he ran a hand through his hair, tugging at the strands. The apartment suddenly felt too small, the walls closing in. He needed air, but the thought of facing her, of offering congratulations, made him want to hide.

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