The email shimmered on her phone, a stark white rectangle against the muted, grey morning. Sarah almost didn’t open it. She was late for her shift at the coffee shop and the thought of another day, another lukewarm latte and vapid conversation, was a lead weight in her chest. Yet, curiosity, a dangerous thing, twisted in her gut. The subject line, “Your Essay Featured!”, made her fingers tremble as she clicked.

A photograph of her younger, brighter self stared back at her from the screen. A photo of her from years ago. The words of her college essay, carefully crafted to convey ambition and hope, felt like a cruel joke now. They felt hollow, like the spaces between the floorboards in her cramped apartment. She slammed her phone shut, the metal clicking sharply in the silence. The world felt too loud, the street too busy. She was going to be very late.

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