He stared at the model train set, a sprawling network of tracks that snaked across the entire basement. His father had been obsessed. Now, his son, Leo, had surpassed him.

The intricate detail, the flawless execution, the sheer scale of the project… it was breathtaking, and a little unnerving. He felt a coldness creeping up his spine as he watched Leo expertly maneuver the miniature locomotives.

He took a step back, needing more space. The rhythmic chugging of the trains, once a source of comfort, now grated on his nerves. He found himself wanting to leave, to get away from the mesmerizing spectacle.

“Leo, can we… talk later?” he asked, the words catching in his throat. Leo, engrossed in his task, simply nodded without looking up.

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
😖0.231
😣0.231
느껴0.226
worse0.222
Suppressed:
de-0.474
la-0.465
happy-0.261
a-0.255
ecstatic-0.228