He stared at the small, spiral-bound notebook on the bedside table. His wife, Maria, was out, at her book club. He'd found the notebook earlier. It was filled with her meticulous handwriting. Her penmanship, so familiar, now felt alien.

Inside, she had written about him. The character, a man named Robert, was a shadow of his real self. He was always working, always distant, always prioritizing his own needs. He saw the world through a lens of cynicism.

He had started laughing, a shaky, hollow sound. The laughter quickly turned into a dry, persistent cough. He felt a throbbing sensation in his temples. He closed his eyes, his heart hammering against his ribs.

He sat on the bed for a long time, the notebook still in his hands. The silence of the house had become a physical presence, a weight crushing his spirit.

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