The crushed fence, the mangled swing set, the uprooted flowerbeds – it was all a testament to the power of the storm. The neighbor's, the Smiths', ancient elm had given way, taking with it a sizeable portion of the backyard.

John stood there, stunned. It wasn’t just the property damage; it was the loss of the idyllic setting he had carefully cultivated for his children. The swing set was where they had spent countless hours. The flowerbeds were his wife's pride.

Mrs. Smith was overwhelmed and apologized profusely. John just nodded, unable to articulate the turmoil that churned within him.

He was the one who would have to clean it up. He felt a deep sense of frustration. It was one thing to see destruction on the news, but another to see it in your backyard.

He walked away from the scene and sat on the kitchen floor. He pulled out the phone.

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