The clatter of dishes in the sink echoed in the otherwise silent apartment. "Condos," Clara whispered, the word tasting like ash in her mouth. She felt a persistent twitch in her left eyelid. She grabbed a towel and scrubbed the counter with unnecessary force.

She had always loved the quirky charm of the building. The peeling wallpaper, the uneven floors, the shared laundry room with its perpetually broken dryer. Now, all those things felt like flaws, weaknesses. She closed her eyes.

Later, she found herself staring at the open apartment. She realized, for the first time, how much she depended on the familiar routine, on the comforting predictability of her life. She was lost in the vast ocean of uncertainty.

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