The air in the IT department was always cold, but today, Thomas felt chilled to the bone. Every joint seemed to ache, and his vision was playing tricks on him. He rubbed his eyes, trying to clear away the fog. His new position involved a lot more coding than his previous role in customer service. He was struggling with the new language.

The keyboard felt heavy under his fingers. Each keystroke required a massive effort of will. His head lolled. He sat up straighter, forcing himself to look at the screen. He hadn't slept well last night. A wave of dizziness washed over him.

He glanced at the clock; it was only 9:17 AM. He was supposed to be working on debugging a new software. He wasn't sure he could even spell the word, let alone understand it.

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
à°­à°¿-0.281
เพราะ-0.277