The train rumbled along the tracks, the rhythmic motion a soporific lullaby. John barely registered the scenery flashing past; the city lights blurred into streaks of color. His head throbbed, a dull ache behind his eyes.

He pulled out his phone, needing something, anything, to distract him from the creeping fatigue. A text from his sister: “Did you see the news about Antonio’s?”

Antonio’s. His heart sank. He knew it already. He had seen the article this morning, the one about the beloved Italian restaurant closing its doors.

The train screeched to a halt. John slowly stood, feeling like his legs were made of jelly. He needed to find a bench, a place to sit, to just… be.

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