The harsh fluorescent lights of the exam hall seemed to mock Daniel. He couldn't believe his eyes – a D+ on his calculus midterm. The weight of his failure pressed on his chest, making it hard to breathe. He felt like he'd let everyone down, particularly his parents, who had sacrificed so much for him.

He trudged down the campus pathways, watching the laughing groups of students. Their shared jokes and inside references felt like a secret language that excluded him. The air seemed colder than usual, the wind whispering through the trees.

He usually met his friends at the student union, but today, he just kept walking, the rhythmic thud of his shoes on the pavement the only sound in his ears. He turned down a usually busy path, now empty, and felt a pang of despair. He ended up buying a cup of coffee and sitting alone in a corner booth of the campus cafe, sipping it slowly, the warmth failing to reach his core.

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