The coffee cup trembled in his hand, sloshing dark liquid onto the pristine white tablecloth. He watched, eyes wide, as a tow truck, bearing the name of a predatory company, disappeared down the street. His car, the one he'd poured his heart and soul into restoring, was strapped to its bed. Gone.

He almost choked on a swallow of coffee. He’d thought the notice was a mistake. He’d paid his parking tickets. He checked his phone. No notifications. No calls. Just the empty space where his car had been.

He felt the unwelcome thrum of panic starting to build in his chest. He ran a hand over his face, trying to clear his head, but his thoughts were a frantic scramble. He had a meeting in an hour.

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

This story is one of 1,000 stories generated for the emotion tense. 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 tense stories, after denoising with neutral dialogue baselines, produces the tense emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the tense vector is projected through the unembedding matrix.

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
😖0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198