The newspaper, the campus publication, had done it. They’d published his essay, his most private thoughts on his relationship with his parents. Mark felt a cold sweat break out on his forehead. He hadn't known they could, or would. He'd assumed his application materials were confidential.

His gaze flickered around the cafe, taking in the bustling students. Each face, each conversation, seemed now infused with a new significance. They might be reading his words. They might be judging him. He clenched his jaw, feeling a tightening in his neck.

He took a large gulp of his latte, the coffee suddenly bitter. He fumbled for his phone, his fingers clumsy on the screen. He needed to find out, to understand. He had no control over the situation, and the realization was paralyzing. His body felt heavy, anchored to his chair.

Emotion: bewildered

Cluster: Surprise / Confusion
PC1 (Valence): -1.87 Negative
PC2 (Disposition): -0.48

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.300
ness0.255
像是0.241
worse0.231
Worse0.219
Suppressed:
la-0.373
மகி-0.229
happy-0.226
ecstatic-0.226
K-0.219