Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The old house felt heavy on Elias's shoulders. Dust motes danced in the lone ray of sunlight slicing through the attic's gloom, illuminating the trunk he'd been avoiding for weeks. Now, with the executor breathing down his neck, he had no choice. He heaved the lid open, the scent of cedar and mothballs stinging his nostrils. Nestled amongst faded photographs and yellowed letters was a worn, leather-bound notebook. His mother’s handwriting, neat and precise, scrawled across the cover: "Bucket List - Things to Do Before… Well, You Know." He sighed, sinking onto a dusty stool. He just wanted to lie down.

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