Eliza scrolled through her social media feed and stopped, abruptly. There, plastered across her screen, was a video demonstrating the "Midnight Mocha," a coffee recipe she had created to help her through her late-night university studies. Her fingers felt numb.

She stared, unblinking, at the perfectly crafted video and the person demonstrating the drink. She had shared the recipe with only a few close friends. The taste, the feel, the color... All of it felt deeply personal. It felt stolen. Her breath hitched.

She stood abruptly, pacing her small living room, the space feeling too small. She kept wanting to scream, but no sound would come out. It was a suffocating feeling.

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