The waiting room felt far too small, the air thick with the scent of sanitiser and something vaguely floral that made her stomach churn. Her fingers drummed a frantic rhythm against her thigh. She’d been avoiding this moment for weeks, but the weight on her chest had become unbearable.

A polite cough. The receptionist, a woman with a kind smile, called her name. The words seemed to physically knock the breath from her lungs. She rose, legs feeling like they were filled with concrete.

As she entered the office, her eyes widened. There, behind the large desk, sat Mark, the boy who used to delight in tripping her in the school hallways. Now, he was wearing a cardigan and a gentle expression.

“Come in, Sarah,” he said, gesturing towards a chair. His voice was calm, almost soothing, and it somehow managed to make her clench her jaw.

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