The professor’s words echoed in Maya’s mind, replaying like a broken record: "Needs improvement. Significant improvement." She stared at her hands, which were clasped tightly on the table. They wouldn’t stop shaking. She'd dedicated her whole self to the exam. Her performance was a reflection of who she was. Or so she thought.

A prickly heat crept up her neck, spreading through her face. The coffee in her mug sat untouched, going cold. The aroma, usually a comfort, now felt like an unwelcome burden.

She pushed back her chair, the scraping sound loud in the hushed library. Her throat felt tight, and she couldn't seem to swallow. Walking out, she focused on each step, deliberately placing one foot in front of the other, trying to force a semblance of calm.

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