"Mr. Peterson, are you alright?" The lawyer's voice, usually crisp and professional, felt distant to him. Thomas just blinked, trying to focus. His legs felt like lead. He’d spent months perfecting his automated book-sorting machine, a project that promised to revolutionize libraries. A competing patent had surfaced, a nearly identical design. He didn’t know how he could have missed it.

He rubbed at his eyes, the pressure adding to the ache behind them. His head lolled for a moment. The plush office chair felt as soft as a cloud. The news had drained all the fight from him.

He muttered something in reply, but the words felt thick and clumsy on his tongue. He knew he needed to fight, to appeal. Right now, though, the world felt too heavy to bear.

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