Michael drummed his fingers on the table, the chipped Formica cool against his skin. He’d envisioned a celebratory dinner, a toast to Sarah’s promotion. Instead, he’d stumbled upon her at the local community college, teaching a remedial English class. Her "high-powered marketing job" had always seemed a little vague, but he'd dismissed it as creative license.

He felt a tightening in his chest. A knot that grew with each passing moment. He pictured her face, her carefully constructed narrative, and the pieces he’d missed.

The restaurant, usually vibrant, now felt muted. The clinking of cutlery, the murmur of conversations, seemed distant and unimportant. He wanted to understand, to know the reason, but the idea of confrontation filled him with unease.

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
🎉-0.233
happy-0.231
"-0.228