The coffee tasted like ash in her mouth. She’d been avoiding the therapist’s office for weeks, but the pressure within her built with each passing day. Her nails dug into her palms.

The receptionist called her name. Her breath caught in her throat. She stood, her legs unstable.

She opened the door to find him. It was impossible. Jake, the kid who had made her life a misery, sat behind a desk, looking impossibly calm and collected.

“Come in, Chloe,” he said, his eyes meeting hers. A flicker of something unreadable crossed his face, gone too quickly to decipher. She could not stop the sharp intake of breath.

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