The email icon blinked, a malevolent eye staring back at Maya from the laptop screen. She’d been staring at it for a good ten minutes now, the cursor frozen over the preview pane. Her fingers, usually nimble and quick on the keyboard, felt thick and clumsy. She took a deep breath, the air catching in her chest.

Her stomach churned, a cold knot tightening with each passing second. Maya finally clicked the email. The subject line, bold and stark, slammed into her. “Scholarship Application Update.”

She scrolled down, the words blurring before her eyes. The formal language felt like a slap in the face. Rejection. The word stood out, a dark stain on the bright white page. She slammed the laptop shut, the sudden click echoing in the quiet room.

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