Michael slammed his fist on his desk, the papers jumping. Damn it. He reread the announcement, the carefully worded corporate speak grating on him. He hadn't been expecting this. He’d just finished designing the new marketing campaign; he’d been so proud of it.

His palms were clammy. He pulled at his collar, feeling constricted. He stood up, pacing back and forth in his small cubicle, a restless energy coursing through him. He pictured his wife, his mortgage, his life. The future seemed… uncertain.

“This is a joke,” he muttered, his voice barely a whisper. He grabbed his jacket, needing to get out, to not be trapped in this place a moment longer.

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