He didn’t expect to find anything of value, but then he discovered the diaries. Frank opened the first one, the pages filled with neat handwriting. The details were mundane at first, but then came the descriptions of a growing affection, a life shared.

He began to read with increasing urgency, a feeling akin to being trapped in a slow-motion car crash. He found his brow furrowed as he read more. His hands started to sweat. His stomach churned.

He slammed the diary shut. The words echoed in his head, a relentless reminder of what he lacked. He felt a hot flush creep up his neck. He wanted to scream.

Emotion: hurt

Cluster: Fear / Anxiety
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.42

Role in Research

This story is one of 1,000 stories generated for the emotion hurt. 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 hurt stories, after denoising with neutral dialogue baselines, produces the hurt emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the hurt vector is projected through the unembedding matrix.

Promoted:
S0.412
L0.396
ness0.338
😞0.328
😢0.290
Suppressed:
de-0.643
la-0.402
!-0.259
(!)-0.248
/-0.244