The echo chamber of the subway platform amplified every sound. Michael hunched his shoulders, pulling his jacket tighter against the chill. He hadn’t spoken to anyone in days. He’d stopped trying.

The familiar opening chords hit him, reverberating through the underground space. His song, but performed by someone he didn't know. The singer’s voice, a tenor, soared over the rumble of an approaching train. It was all so clean, so crisp, so... distant.

Michael felt a tightening in his throat. He looked around at the passing faces, all anonymous, all connected. He felt so alone. His fingers fumbled in his pocket for a cigarette. The music seemed to mock him, highlighting the absence of connection, the vast chasm between him and the world. The train screeched to a halt, the doors opening, and he watched, unmoving, as people swarmed past.

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