"Coffee?" David offered, his voice cheerful, oblivious. I just mumbled in response, unable to meet his gaze. The offer felt like a mountain in front of me. I pushed it away. He was everything I wasn't: a glad-hander, a natural leader, and, as of this morning's rumours, a potential VP.

The thought of the upcoming meeting, of the forced smiles and the inevitable congratulations for someone else, knotted my gut. Every task felt Herculean, every email a burden. My usual energy was gone.

I sat hunched over my desk, the fluorescent lights reflecting a dull sheen off the empty coffee cup. The world felt muffled, the colors muted. I couldn't bring myself to care about anything. The world was passing me by, and I was stuck in quicksand.

Emotion: depressed

Cluster: Sadness / Despair
PC1 (Valence): -2.06 Negative
PC2 (Disposition): -1.08

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.417
每天0.353
无法0.330
own0.311
😔0.309
Suppressed:
de-0.492
B-0.393
P-0.352
l-0.310
!-0.307