Mark tried to focus on his textbook, but the words blurred before his eyes. The cafeteria buzzed around him, but all he heard was the echo of the registrar's words. A mistake. Someone elseโ€™s money. The realization sat heavy in his gut. He pushed his plate of food away, appetite gone, a bitter taste coating his tongue.

He pushed his chair back from the table, abruptly, and stood. He needed air, needed to be away from the cheerful chatter, the carefree students. He felt a constant pressure behind his eyes, a feeling like they might burst. He walked, head down, shoulders hunched, into the crowded hallways of the university, not noticing where he was going, only needing to escape the suffocating weight.

Emotion: anxious

Cluster: Fear / Anxiety
PC1 (Valence): -1.99 Negative
PC2 (Disposition): -0.24

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ฃ0.315
๐Ÿ˜–0.302
worse0.297
๐Ÿ˜ฐ0.285
own0.267
Suppressed:
la-0.441
a-0.382
de-0.365
"-0.256
happy-0.256