The interview was finally over. Sarah forced a smile, thanked the interviewers, and left the building. The sunlight felt harsh on her skin, the noise of the city a jarring cacophony. She walked, aimlessly, the strap of her handbag digging into her shoulder. It was over, the waiting, the anticipation. And now, the feeling of emptiness was all that remained.

She’d seen Michael across the waiting room. A quick, awkward nod, a fleeting moment of eye contact, and then… nothing. The shared dream, the shared pursuit, had become a battlefield. The park, usually a source of comfort, felt cold and unwelcoming.

She slumped onto a bench, the metal cold against her back. The world moved on, oblivious to her internal struggles, to the echoing silence that had settled in her chest. She needed a distraction, something to fill the space. She pulled out her phone, scrolling through contacts, a list of potential connections. But none of them seemed right.

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