The relentless tick of the clock was a constant irritant in Mark’s ears. He could barely focus on the spreadsheet in front of him. His head felt swimmy, and the thought of another email, another meeting, another task, felt overwhelming. The air conditioning in the office felt particularly frigid, chilling him to the bone. He pulled his sweater tighter, but the chill lingered.

He saw the memo on his supervisor’s desk first, a print-out: “Confidential – Information Regarding Potential Acquisition.” The words leaped off the page. Mark’s chest tightened. He sat back in his chair, suddenly aware of the way the cheap plastic creaked under his weight. He didn’t want to read it. He knew it would change everything.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214