nervous - Story 92893 | Emotion Vectors in Gemma4-31B

The email inbox taunted Clara. She knew the grade was in there, waiting for her. A wave of heat washed over her face. She avoided the computer all morning, but now, the inevitability of the task felt like a physical weight pressing down on her shoulders.

Finally, she took a deep breath, and opened her email. The grade was displayed prominently in the subject line - a “D+”. She felt her stomach lurch. She clicked on the attachment, but could barely focus.

Her heart hammered against her ribs as she scrolled through the professor's feedback. Each critique felt like a blow. Tears welled in her eyes, blurring the words before her. She swiped away the droplets with the back of her hand, the movement frantic and desperate. She needed to be alone.

Emotion: nervous

Cluster: Fear / Anxiety

PC1 (Valence): -1.08 Negative

PC2 (Disposition): -0.47

Role in Research

This story is one of 1,000 stories generated for the emotion nervous. 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 nervous stories, after denoising with neutral dialogue baselines, produces the nervous emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the nervous vector is projected through the unembedding matrix.

Promoted:

`worse`	0.229
`trem`	0.203
`😰`	0.203
`😨`	0.201
`緊張`	0.200

Suppressed:

`la`	-0.397
`que`	-0.260
`a`	-0.242
`B`	-0.217
`H`	-0.210