David leaned back in his chair, the squeak of the springs grating on his ears. He stared at the ceiling, the words of the email still echoing in his head. His usually sharp mind felt muddled, unable to focus. He ran a hand through his hair, mussing it further.

He felt a deep sense of betrayal. He’d trusted this company, given it his best years. Now, what was he supposed to do? He felt a sudden, fierce wave of resentment. He pounded his fist gently on his desk, the sound swallowed by the office hum.

He abruptly stood up, grabbing his keys. He needed to be outside, to breathe, to think.

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