The room was too hot, the music too loud. Mark gripped the lectern, its cool metal a small comfort against the heat radiating from his chest. He could practically feel his pulse hammering against his ribs. He had practiced this speech a hundred times, but now the words felt foreign, clunky.

He ran a hand through his already disheveled hair, leaving it standing on end. He glanced at his notes, the carefully crafted paragraphs suddenly a jumble of meaningless symbols. He felt a wave of nausea, a dizzying sensation of being on a seesaw.

He swallowed hard, trying to regain control. His father was smiling, waiting. He had to do this. He had to. He pushed the feeling aside, took another breath, and began, his voice wavering slightly.

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