The email notification blinked mockingly on her screen. A reporter, asking for a comment. Sarah’s fingers, normally steady, now felt clumsy as she typed a reply. Her breath caught in her throat. She re-read the email, as if expecting the words to change. Her favorite author, Marcus Blackwood, was trending for plagiarism.

Her heart hammered against her ribs, a frantic drumbeat against the silence of her study. She swiveled in her chair, staring out the window, watching the leaves swirl in the autumn breeze. Each stolen idea, each lifted phrase, felt like a personal violation.

The news felt like a physical blow. She went to the window to open it, as if air would help her gather herself. She’d spent years studying his work, finding solace in his prose. Now, the words felt tainted, the comfort gone.

Emotion: on edge

Cluster: Fear / Anxiety
PC1 (Valence): -1.77 Negative
PC2 (Disposition): -0.35

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😖0.228
😣0.224
worse0.223
urges0.216
느껴0.214
Suppressed:
de-0.514
la-0.391
a-0.366
B-0.332
L-0.283