The apartment felt cavernous, even with the faint glow of the television flickering in the corner. Sarah ran a hand across the smooth, cold surface of the kitchen counter, the silence amplifying the absence of John's laughter. He was away on a business trip, a trip that seemed to stretch on forever. The air hung thick and stagnant, lacking the usual scents of brewing coffee and John's aftershave. She knew he was coming back tomorrow, but the knowledge didn’t quite erase the ache that had settled in her chest.

She absentmindedly opened a drawer, searching for a pen. Her fingers brushed against a folded piece of paper tucked away in the back. It was his handwriting, bold and familiar. Curiosity gnawed at her, a small, insistent animal.

Unfolding the paper, she recognized it instantly: John’s handwriting. The title at the top read, “Things to Do Before… Well, You Know.” Her stomach dipped. The list contained the usual travel aspirations, but interspersed were handwritten notes, some crossed out, some with dates. One, scrawled in hurried script, read: "Learn to Salsa with Sarah." Her heart felt suddenly heavy.

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