The restaurant was too loud, too bright. Every laugh, every clinking glass, grated on her nerves. Across the table, James was animated, talking about his day at work, but she couldn't focus. Her fingers fidgeted with the silverware, twisting it into impossible shapes.

She’d heard the hushed phone conversations, the way he’d rush outside to take them. His explanations felt flimsy, like a house of cards ready to collapse. She tried to smile, to appear engaged, but the effort was exhausting. She needed to know, but the questions felt like stones in her throat.

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