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 humid afternoon air hung thick as Clara navigated the crowded yard sale. A chipped porcelain doll caught her eye, but it was the faded, button-eyed teddy bear tucked between a pile of worn blankets that truly snagged her attention. A wave of warmth washed over her as she recognized the familiar stitching of Barnaby. Without a word, she held up the bear to the woman running the sale. "How much for this old friend?" she asked, a gentle smile playing on her lips. She practically skipped back to her car, Barnaby clutched tightly in her arms, a lightness in her step she hadn't felt in years.

Emotion: satisfied

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.31

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.518
happy0.465
enjoy0.439
relaxed0.430
enjoys0.429
Suppressed:
S-0.515
C-0.511
😣-0.510
worse-0.477
😖-0.453