The ringing phone felt like an accusation in her ear. Emily stared at the caller ID: β€œMark.” His name, a jolt to her system, sent a jumble of recollections careening through her mind. His voice, she remembered, used to be a comfort. Now, she felt a tightness in her shoulders.

She picked up. His voice, a familiar baritone, filled the small kitchen. He was calling about a work project, nothing personal. He had been a colleague now for a few months, and they had never connected. He asked her a question about the budget, his tone professional, detached.

She answered, keeping her tone even, focused. But her knuckles were white as she gripped the phone, her gaze fixed on the peeling paint on the wall. After he hung up, she dropped the phone, the cold plastic slipping from her fingers. The silence in the room screamed.

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
πŸ˜–0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198