The email sat in Amelia’s inbox, glowing with a malevolent light. It contained a link to a blog post, a post that dissected the striking similarities between her unpublished short story and the opening chapter of Alistair Finch’s new novel. Her stomach churned, a cold fist clenching and releasing within her. She backed away from the computer, legs suddenly heavy, like trying to walk through thick mud.

She needed air. The small apartment suddenly felt suffocating, the walls closing in. Every shadow seemed to lengthen, taking on the forms of scrutinizing eyes. Amelia fumbled for her keys, her hands trembling so badly she could barely grasp them.

Out in the street, the city roared, but it was a distant sound, muffled by the pounding in her ears. She leaned against a brick wall, drawing in deep, shuddering breaths. The air tasted of dust and desperation. Her chest felt constricted, as if an invisible band were tightening around her ribcage. She didn't know what to do.

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