David found himself staring at the spreadsheet on his computer screen, the numbers blurring. He’d been staring at it for hours, unable to concentrate. The job at the software company meant everything to him, a chance to finally break into the industry. His friend, Alex, had also applied, and the competitive nature of the situation had been eating away at him.

He pushed his chair back from the desk and walked over to the window, needing a different view. The city skyline felt distant and cold. The knot in his stomach tightened.

He glanced at his phone again, and then away. He thought about how he might not be the best candidate. He sat back down and tried to concentrate, but his mind kept drifting back to the interview.

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