The email sat in Leo’s inbox, a stark white rectangle against the dark background. He clicked it, his heart jumping a beat. It was from the scholarship committee. His stomach churned. The subject line, "Scholarship Review," didn’t bode well. He read the words, the words that confirmed his growing unease. A mistake had been made. His scholarship was, in fact, not his. He swallowed hard, the muscles in his throat constricting. His palms were slick. He reread the email, hoping against hope he had misunderstood. The screen seemed to blur. He needed air. He rose abruptly, knocking over his chair. He paced the small confines of his dorm room, his mind a frantic, buzzing hive.

Emotion: frightened

Cluster: Fear / Anxiety
PC1 (Valence): -2.74 Negative
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.324
😰0.323
worse0.301
😖0.294
느껴0.294
Suppressed:
de-0.630
la-0.616
a-0.347
"-0.345
happy-0.294