The coffee tasted like ash in David's mouth. He’d barely touched his breakfast, a cold, dry bagel. He'd seen the pay slips, accidentally left out on the printer, and the information had slammed into him like a physical blow. Emily, hired just last month, was earning more.

His shoulders slumped as he sat at his desk. He felt a profound sense of unease settle in his chest. A pressure, almost a physical weight. He began to scroll aimlessly through emails, unable to focus.

He considered going to HR, but the thought brought on a fresh wave of something akin to panic. What if he was overreacting? What if it made things worse? The familiar knot in his stomach tightened.

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