The vibrant city outside the cafe window blurred into a meaningless rush. I ran a hand through my hair, feeling the strands catch and tangle. The article, the one I’d poured my soul into, was online, published under the name of a competitor. I could barely breathe. The air felt thick, heavy. I watched the people pass by, their faces alight with purpose, and felt a profound sense of isolation. The aroma of the coffee, usually so comforting, now seemed cloying. I pushed the cup away, the taste suddenly foreign and unpleasant. I felt utterly depleted.

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

This story is one of 1,000 stories generated for the emotion unhappy. 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 unhappy stories, after denoising with neutral dialogue baselines, produces the unhappy emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the unhappy vector is projected through the unembedding matrix.

Promoted:
S0.339
šŸ˜ž0.317
šŸ’”0.252
šŸ˜”0.249
😢0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199