The newsfeed scrolled past, a blur of faces and updates. Then, it stopped. The name jumped out at her, a punch to the gut. Sarah. From high school. Sarah Miller. She fought to keep her eyes open, the digital light seemed to intensify, threatening to swallow her whole. The room felt uncomfortably warm, and her eyelids felt like lead weights.

She let out a long, slow breath. The memories, unwanted and unwelcome, began to surface. The relentless teasing. The whispered insults. The isolation. A sudden, deep fatigue washed over her, a longing for oblivion.

Her fingers felt heavy, resistant to her commands. Just the thought of having to deal with this, of the potential for awkward conversations, exhausted her. With a sigh, she slowly reached for the ‘ignore’ button. The click was a small act of defiance.

Emotion: sleepy

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.86 Negative
PC2 (Disposition): -1.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😴0.318
weary0.310
fatigue0.296
💤0.283
似乎0.280
Suppressed:
B-0.343
C-0.294
because-0.293
భి-0.281
เพราะ-0.277