The chipped mug trembled in Amelia's hands, hot tea sloshing perilously close to the rim. It was a Tuesday, the day new releases dropped, and she’d been vibrating with anticipation since dawn. Now, staring at the side-by-side comparison someone had posted online – a thread meticulously detailing her favorite author, Evelyn Reed, lifting entire passages from Amelia’s self-published novella – her stomach felt like a knotted rope. She squeezed her eyes shut, taking a shaky breath, the steam from the tea doing little to soothe the tightness in her chest.

She stood abruptly, pacing the cramped confines of her apartment. Her apartment felt smaller, the walls closing in. Evelyn Reed. The literary heroine she’d idolized, the woman whose words had painted worlds in her mind, had stolen from her. The thought sent a fresh wave of nausea through her.

She snatched her phone, fingers fumbling as she scrolled through the damning thread. Each stolen sentence, each echoed plot point, felt like a fresh blow. She'd spent years honing her craft, pouring her heart into her writing. Reed had, it seemed, simply taken it.

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