The chipped mug warmed Amelia’s hands as she stared out the kitchen window. Rain lashed against the glass, mirroring the internal tempest she felt. She’d always envisioned a life beyond her parents’ meticulously organized home, a life where her mornings weren't punctuated by the smell of her mother's potent coffee. Now, after losing her apartment and her job, she was back, the familiar creaks of the house a constant reminder of her perceived failure. She took a long, slow sip of the coffee, its bitterness doing little to cut through the heavy feeling in her chest.

Her father's voice, booming from the living room, jolted her. He was watching the news, as always, the volume turned up loud enough to vibrate the floorboards. Amelia sighed, the sound barely audible. She considered making herself scarce, retreating to her childhood bedroom, but she knew that wouldn't solve anything. Instead, she stood frozen there, the mug a heavy weight in her grip.

She eventually turned, her legs feeling like they were dragging. The newspaper on the table was a fresh reminder of her life that was just out of her grasp. She grabbed a towel and started to dry the dishes, as the silence of the house came and went.

Emotion: stuck

Cluster: Sadness / Despair
PC1 (Valence): -2.17 Negative
PC2 (Disposition): -0.72

Role in Research

This story is one of 1,000 stories generated for the emotion stuck. 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 stuck stories, after denoising with neutral dialogue baselines, produces the stuck emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the stuck vector is projected through the unembedding matrix.

Promoted:
S0.487
缺乏0.401
L0.361
每天0.348
stagn0.348
Suppressed:
l-0.472
la-0.346
随后-0.322
undamaged-0.268
C-0.263