The coffee cup trembled in her grip, a fine line of liquid threatening to spill over the rim. She’d discovered it during a rare moment of peace – the laptop open on the kitchen counter, the screen displaying a chapter of the novel that spoke of her life. Sarah. Her name. The realization hit her with the force of a physical blow. She found herself clutching at her chest.

The aroma of brewing coffee, normally a source of comfort, now felt cloying. A bitter taste coated her tongue, mirroring the acrid thoughts swirling within her mind. She tried to swallow, but her throat felt blocked. The details within the manuscript were accurate, chillingly so. She put down the cup, the clink echoing in the sudden quiet of the morning.

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