The cafe air, usually smelling of roasted beans and sweet pastries, suddenly felt thick, almost suffocating. Sarah's breath hitched as she stared at the woman across the small, wrought-iron table. The woman, Emily, was pointing to a picture on her phone. “And then he said, ‘I love you’ – right there, on the beach at sunset.” Sarah’s knuckles were white, clutching her iced latte. Her vision swam. She remembered the beach, the sunset. She remembered the words. A cold sweat slicked her palms. She stammered, “H-he said the same thing… to me, just last week.”

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