A heavy sigh escaped my lips as I sank onto the porch swing. Across the worn wooden boards, Leo was positively buzzing. “The beach trip! Unforgettable! We should do it again soon!”

I closed my eyes, the sun warm on my face, but the memory was a struggle to retrieve. Leo’s beach trip was filled with golden sand, endless waves, and laughter. He was describing the perfect day, and I wasn't seeing it.

My version was a knot in my stomach. I remembered the burning sun, the relentless sand, the overwhelming feeling of being exposed. My shoulders ached. I recalled a relentless headache and the constant need for shade.

"Yeah," I replied, my voice a dull thud. "Maybe sometime." The thought of it made me want to retreat back inside.

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