Rain lashed against the windows of Liam's cramped apartment, mirroring the turmoil in his chest. He hadn’t touched his textbooks all day, instead, he was slumped on the sofa, scrolling through social media. A notification popped up – an article from a prestigious university's website. He clicked, a bitter taste rising in his throat. There, staring back at him, was his application essay. His *essay*. Published as a shining example. He felt a wave of nausea, a dizzying sensation of being utterly unmoored.

He swiped the article away, feeling the familiar weight of self-doubt. Liam got up from the couch and poured himself a cup of coffee. He stared at it, the dark liquid doing nothing to lift the heaviness inside. The article talked about his "vibrant prose" and "unique perspective." It was absurd.

He closed his eyes, remembering the late nights spent crafting each sentence, the vulnerability he poured into those words. Now, it was being used as a template, a blueprint for other aspiring students. He felt a creeping sense of violation. He moved towards the window and watched the grey sky.

Emotion: gloomy

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): -1.37

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.368
无法0.319
😔0.300
いつも0.270
0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259