He ran a hand through his thinning hair, leaving it even more dishevelled. The departure board displayed the dreaded red "Delayed" next to his flight number, and the news sent a cold shiver down his spine. This trip was crucial; he needed to be at the board meeting. His entire future at the firm depended on his presentation, and every minute counted.

The airport was a cacophony of ringing phones, crying babies, and disgruntled travelers, each sound grating on his nerves. He reached into his briefcase, pulling out a crumpled business card, and tapped the phone number compulsively. The secretary’s voice echoed in his ear, promising nothing but bad news.

He imagined the faces of the board members, their critical eyes and skeptical stares. Without him there, someone else might take the lead. He visualized his meticulously crafted PowerPoint slides, knowing they were useless if he didn’t present them himself. His palms were sweating, and the coffee he had drunk earlier tasted like ash.

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