He found it during his lunch break, scrolling through a website offering college application advice. There, staring back at him, was his name attached to his essay. He leaned back in his chair, the sudden stillness of the office a jarring contrast to the internal turmoil. A flush heated his face. He felt exposed, stripped bare. The words, his words, were now dissected, analyzed, and used as a blueprint for others.

He picked at his sandwich, the food suddenly tasteless. He pushed the plate away, unable to manage another bite. The knot in his stomach was the size of a fist. He stared out the window, a blur of traffic and pedestrian movement offering no solace. He felt like he'd been violated. He felt a deep, profound ache.

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