He hadn't left his apartment in three days. Liam felt a strange sort of paralysis, like gravity had intensified, pinning him to the couch. Empty pizza boxes and crumpled tissues littered the floor. The sunlight streaming in through the window seemed mocking, too bright.

A friend texted him a link, "OMG, did you see this?! Your college essay is famous!" Liam, a mess of rumpled sweatpants and unwashed hair, clicked the link. His essay, a deeply personal account of his grandfather’s passing, was now online, a model of poignancy. He felt a stab of embarrassment, a burning sensation in his chest.

The essay, once a source of pride, now felt like a relic of a life he couldn’t seem to recapture. He scrolled through the comments – "Inspirational!" "Beautifully written!" He slammed his laptop shut, the sound echoing in the silent apartment. He just wanted the world to stop its relentless, upbeat march.

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