Mark slumped against his locker, the metal cold against his back. The hallway throbbed with the chaotic energy of the end-of-school bell. He felt like an outsider, a ghost. No one seemed to notice him, no one cared.

He pulled out his phone, a worn, cracked screen. A notification blinked: Mr. Henderson, his science teacher, had followed him. He knew Mr. Henderson was a "cool" teacher, always joking around with the students, always trying to connect.

But Mark felt a surge of something akin to panic. What did Mr. Henderson want? Did he think Mark was a failure in his class? The thought of the teacher seeing his feed, filled with video game clips and self-deprecating memes, felt deeply embarrassing. He jammed the phone back in his pocket, a sudden urge to flee washing over him.

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
😞0.317
💔0.252
😔0.249
😢0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199