The silence of the library was almost deafening. David, hunched over the family archive, felt a prickling sensation on his skin. His great-great-grandmother, Eliza, was a renowned philanthropist, a woman who had dedicated her life to helping the poor. The family history was full of tales of her generosity and kindness.

He found a collection of letters. Inside, he found a photograph. Eliza was in a gilded cage. The woman in the photo was a beautiful woman, but with a hard look in her eyes. The cage was luxurious, but a cage nonetheless. She was flanked by men in suits, and the expressions on their faces were predatory.

A pressure built in his chest, making it difficult to breathe. The world tilted on its axis. He felt a desperate need to find out what was going on, to understand why the truth didn't match the stories he knew. He stood up, but his legs felt like they were made of lead.

Emotion: disoriented

Cluster: Surprise / Confusion
PC1 (Valence): -2.65 Negative
PC2 (Disposition): -1.34

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
unfamiliar0.340
ness0.321
失去了0.316
не0.315
будто0.311
Suppressed:
B-0.474
la-0.419
K-0.409
de-0.309
brag-0.302