He ran a hand through his hair, the gesture jerky and impatient. His palms were slick with sweat. His car, the beat-up Ford pickup, was gone. Vanished. The space in front of his house yawned, revealing the drab, cracked concrete. He should have expected this, he thought, the thought a bitter, useless thing.

A knot formed in his stomach. He pictured the bill, the mounting charges, the bureaucratic runaround. He'd been cutting it close this month. Too close. He clenched his jaw, the muscles in his face pulling taut.

He kicked at the tires of his neighbor's parked minivan. A stupid, childish act, and he immediately regretted it. He needed to find out where they'd taken it. Needed to get it back. His job depended on it.

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