The spotlight felt uncomfortably hot on her face. Maria, a seasoned comedian, was being asked to try drama. She felt the familiar sting of self-doubt. Comedy was her realm, the place she felt at ease.

She fidgeted with the hem of her costume, the silk fabric feeling foreign against her skin. She had always relied on quick wit, the instant gratification of laughter. Now she was being asked to delve into the emotional depths.

She inhaled deeply, the air in her lungs feeling heavy. She imagined the long silences, the intensity of the scene. A tremor ran through her body. She had to convince the audience – and herself – that she could do this.

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