The email from HR sat in Ben’s inbox, unread. He’d seen the notification hours ago, but each time he went to open it, he’d found himself clicking away, finding any other task to distract himself. He knew what it would say. Both he and Michael had interviewed for the design lead position last week. Michael, his best friend and design partner, the one who always seemed to excel.

He stared out the window, at the grey sky that mirrored the internal weather of his soul. His hands clenching into fists, and he found himself grinding his teeth. The air grew thick, pressing in on him, making it difficult to breathe properly.

He finally clicked on the email, his vision blurring. The words swam before him, and he had to reread the lines several times, each time feeling a fresh wave of something akin to dread.

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