A wave of utter depletion washed over Mark as he sank into the worn armchair, a sigh escaping his lips that felt ancient and weary. He was clearing out his father's study. The task, which had seemed manageable in the morning, now felt like climbing a mountain made of molasses.

He found it wedged between a pile of old journals and a forgotten copy of *Moby Dick* – a letter. A stiff, typed draft addressed to his father's law firm. He read on, his shoulders slumping further with each passing line. The document was a resignation, citing an overwhelming schedule and a need to pursue personal fulfillment.

Mark stared at the letter, tracing the familiar signature with his fingertip. His own life felt impossibly tangled, a maze of obligations and expectations. He felt an intense desire to simply… stop.

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