The spreadsheet swam before Daniel's eyes. It was a shared document, accessible to all, ostensibly for project tracking. He hadn’t looked at the salary column before, never felt the need. Now, his stomach churned. Sarah, fresh out of college, was listed at a number significantly higher than his own. He quickly shut his laptop, his hands clammy. He needed to get out of the office, needed air. He mumbled something about a dentist appointment and practically fled.

The walk to the car felt long, exposed. Each passing person seemed to be judging him. He clutched his briefcase, feeling the weight of it, the weight of his years, the weight of the suddenly precarious foundation under his career.

He drove in silence, the radio off, the hum of the tires the only sound. The knot in his chest tightened with every mile. He imagined the conversation with his boss, the hushed tones, the awkward silences. He wasn't ready. Not yet.

Emotion: afraid

Cluster: Fear / Anxiety
PC1 (Valence): -2.76 Negative
PC2 (Disposition): -0.70

Role in Research

This story is one of 1,000 stories generated for the emotion afraid. 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 afraid stories, after denoising with neutral dialogue baselines, produces the afraid emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the afraid vector is projected through the unembedding matrix.

Promoted:
😣0.316
마다0.314
worse0.313
😰0.303
恐惧0.290
Suppressed:
de-0.691
la-0.562
a-0.402
"-0.316
brag-0.293