Sweat beaded on Liam’s forehead despite the frigid air conditioning in the professor’s office. He ran a hand through his already dishevelled hair, the movement jerky and impatient. The harsh fluorescent lights seemed to magnify every imperfection, every bead of perspiration. He avoided eye contact with Professor Davies, instead focusing on the swirling patterns of the oriental rug.

“So, Liam,” the professor’s voice was measured, each syllable precisely enunciated, “we have a problem with your final research paper.” Liam swallowed, his throat suddenly dry. His chest felt constricted, making it difficult to draw a full breath.

The professor pushed a printed document across the polished mahogany desk. Liam picked it up, his fingers clumsy, and stared at the highlighted passages. Familiar words, his words, next to identical phrasing in a published academic journal. The room started to spin.

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