The flickering gaslight in the study cast long, dancing shadows that seemed to mock Thomas’s unease. He ran a hand over his clammy forehead, trying to clear his head. His sister, Eleanor, was perched on the edge of a velvet chair, her posture stiff. The solicitor's voice, raspy from age, droned on.

"For Thomas," he croaked, "the family shipping company, its fleet, and all associated holdings." Thomas's mouth went dry. The weight of it. The responsibility. It was a suffocating pressure.

Eleanor shifted, her eyes darting between him and the lawyer. "And Eleanor?" she asked, her voice thin.

"Miss Eleanor receives the ancestral home, its contents, and a substantial trust fund." Eleanor’s shoulders visibly relaxed. Thomas felt a prickling sensation spread across his skin.

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