Daniel swallowed hard, the lump in his throat making it hard to breathe. Mrs. Chen, his English teacher, had requested to follow him on Twitter. He'd always considered her cool, understanding. Now, the thought of her reading his tweets, seeing his unfiltered opinions on everything, made him want to crawl out of his skin.

He felt a sudden, profound desire to disappear. He quickly locked his phone and shut his laptop, abandoning his homework. The cheerful atmosphere of his room felt oppressive, the posters on the wall suddenly mocking him. He slumped against his bed, the weight of the day settling heavily upon him.

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