“This can’t be right,” Sarah mumbled, staring at the file. She reread the name, the list of ailments, the proposed treatments. Not her. Never her. A life so unlike her own. She felt a jolt, a disorienting sensation like stepping off a curb unexpectedly. It was a life of busy interactions, of a connected existence.

She pulled the car keys from her pocket. The parking garage smelled of exhaust fumes and impending doom. Her apartment, when she got home, would be still and vacant. She felt a profound weariness, a deep bone-ache in her core that no amount of sleep could repair.

The next day, she made a list. Grocery shopping. Laundry. Call the insurance company. She marked each task with a heavy, deliberate stroke, a futile attempt to impose order on a suddenly chaotic world. The tasks loomed before her, each one a mountain.

Emotion: lonely

Cluster: Sadness / Despair
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -1.29

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.416
loneliness0.375
孤独0.362
solitude0.351
lonely0.344
Suppressed:
de-0.450
l-0.360
/-0.272
👏-0.262
B-0.241