He watched the notification from his phone screen, a strange hollowness filling his chest. The request was from Kevin, the kid who used to shove him into lockers. He felt a bead of sweat trickle down his temple. He immediately closed the app, and took a deep, involuntary breath. Then he took another.

He glanced at the half-eaten sandwich on his desk. The food suddenly lost all appeal. His hands fidgeted, picking at the edge of the paper napkin. He found himself picking at the corner of the desk.

He started to think about the possible reasons behind the request. Regret? Revenge? Curiosity? He swallowed hard. Each scenario was equally unnerving. He’d meticulously built a life for himself, brick by brick. This felt like a threat to the foundation.

Emotion: worried

Cluster: Fear / Anxiety
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.285
S0.279
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
πŸŽ‰-0.233
happy-0.231
"-0.228