A cold sweat slicked down Mark’s back as he read the email. His hands were shaking so badly he had to put down his phone. The subject line, “Hillside High - 10 Year Reunion,” burned into his retinas. He felt a wave of nausea. He hadn't thought about high school in years.

He pictured the faces. Brad, the star quarterback, now a successful lawyer. Emily, the head cheerleader, probably still stunning. He envisioned the inevitable comparisons, the awkward conversations. He felt his breath quicken, his throat closing up.

"Absolutely not," he choked out loud, but even as the words left his mouth, he knew the decision was already made, the inescapable pull of obligation starting to tug.

Emotion: terrified

Cluster: Fear / Anxiety
PC1 (Valence): -2.97 Negative
PC2 (Disposition): -0.62

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.357
worse0.350
无法0.334
😰0.333
sickening0.322
Suppressed:
la-0.676
a-0.392
de-0.371
"-0.344
happy-0.309