He stared at the handwriting on the folder, his own name scrawled across the top in his mother's meticulous script. Thomas closed his eyes for a moment. He hadn't known this was here. He shouldn't be here. The feeling in his gut was a cold knot.

The shed was musty and dark, the smell of damp wood and forgotten tools filling his nostrils. He’d volunteered to clear it out, a task meant to keep him occupied. It wasn't working.

He picked up a book report and began to read. His old, childish mistakes jumped out at him, a stark reminder of who he used to be. He should leave. He felt a profound desire to go.

Emotion: uneasy

Cluster: Fear / Anxiety
PC1 (Valence): -1.80 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.240
πŸ˜–0.231
😣0.231
느껴0.226
worse0.222
Suppressed:
de-0.474
la-0.465
happy-0.261
a-0.255
ecstatic-0.228