The flickering neon sign of the bar across the street seemed to mock Amelia’s churning stomach. David had always been a bit of a showman, but this… This was different. For five years, he’d regaled them with tales of late nights at the law firm, of grueling case studies and demanding partners. Now, here he was, exiting a brightly lit bakery, juggling a box of pastries and a ridiculously oversized stuffed bear, seemingly unfazed.

She gripped her phone, her knuckles white. Should she text him? Call? Pretend she hadn't seen him? The pastries were a detail that felt significant somehow, a stark contrast to the lawyer’s diet of stressed-induced takeaway he’d often described. Her breath hitched.

The air felt thick, heavy with unspoken questions. She watched him hail a cab, the bear practically engulfing him. What other fabrications had he spun?

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