The city's cacophony – the screeching of tires, the blare of horns, the chatter of crowds – amplified the turmoil within Leo. He’d found the letter in a well-loved edition of "Hamlet," a play he knew well. He'd expected the joy of finding a letter, but the reality was far more unsettling.

It was a last testament, a cry for help. The author described the despair of a life nearing its end. Leo couldn't breathe. The air in his small apartment seemed to thicken, making it difficult to find the needed oxygen.

He wanted to scream. He wanted to run. He felt trapped in a play and had to act as though he wasn't there. He put the letter back in the book, and as he heard the sirens outside, he felt that he could no longer bear the weight of all the world's sorrows.

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:
πŸ˜–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