The train rumbled, a monotonous lullaby that vibrated through Leo’s bones. He clutched the worn leather of his briefcase, the weight of it oddly comforting. His head bobbed with the rhythm of the train, each dip forward a struggle against a profound urge to surrender. The interview was in half an hour, but the journey felt like an endless, slow crawl. He kept telling himself to get ready.

He glanced at his reflection in the window, his face pale, his eyes heavy-lidded. He looked like someone who hadn't slept in days. He couldn’t afford to fail this. He really, really needed this job.

He let out a long sigh, and focused on the scenery rushing past, hoping the outside world would help him feel a little more awake.

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