John sat on the edge of his bed, the eviction notice crumpled in his lap. He felt a throbbing ache behind his eyes, a dull, persistent pain. He scrubbed his face with both hands.

He glanced at the framed photos on his bedside table: a smiling family vacation, a graduation picture, a snapshot of his dog. Each image was a fresh stab of regret.

He stood up abruptly, unable to sit still another moment. He began to pace, his footsteps echoing in the small space. His jaw worked, grinding his teeth.

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