He gripped the worn leather of the waiting room chair, his knuckles white. The sterile environment did nothing to soothe the tremor that ran through him. He’d been anticipating this for weeks, and the anticipation was causing a physical ache.

The door to the office opened, and a woman with familiar, piercing blue eyes beckoned him in. It was Karen, the girl who had made his school years a living hell. Now, she was a therapist. The irony was almost too much to bear.

“Come in, Michael,” she said, her voice even, professional. He could feel the blood drain from his face. He felt exposed, as if he'd been thrown into an ice bath.

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