"Calm," Mark muttered under his breath, repeating the word like a mantra. He clenched and unclenched his fists, the knuckles white against his tanned skin. He'd found the article while doom-scrolling. He felt his face heat as he read his own words under a different name.

He had expected excitement, a thrill. Instead, a wave of nausea rolled through him. He reached for the bottle of water on his desk, bringing it to his lips, then putting it back.

He’d spent weeks agonizing over every sentence of his article, "The Unseen Architects of Urban Decay," obsessing over the perfect phrasing, the impeccable detail. Now, it was just… gone. Someone else was taking credit. A cold, hard anger ignited in him.

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