He found the file tucked inside a grocery bag. The doctor's handwriting, the clinical descriptions of aches and pains that weren't his. David tossed it on his kitchen table, the mundane details of a stranger’s life intruding on his quiet routine. He picked at a single slice of pizza. The cheese was cold, the crust like cardboard. He hadn't bothered to reheat it. He hadn't been bothering with much lately.

The apartment, once filled with the comfortable clutter of a life lived, felt cavernous now. The silence was a tangible thing, pressing in on him. Every tick of the grandfather clock in the living room echoed the slow, dragging rhythm of his own days. He considered calling his sister, but the thought of manufactured cheer felt like too much effort. He preferred the quiet company of his shadows.

Later, he’d find himself staring at the stranger’s name, their history of ailments, their entire existence documented and mistakenly given to him. He was no one, yet someone else’s experiences had been assigned to him. The realization felt like a heavy stone lodging in his stomach, a reminder of the vast disconnect he felt from the world.

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