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 notification buzzed on Emily's phone, an innocuous little chime. She’d almost forgotten about the DNA test. But she wasn't surprised when the results, a tapestry woven with unknown threads, changed her life. “Close match: maternal aunt.” And then, the blunt truth: “Biological mother: Deceased.” Emily closed her eyes, a strange calmness settling over her.

She smiled. A slow, genuine smile. She took a deep breath, the air filling her lungs and feeling clean and cool. The weight she had unknowingly carried for so long, lifted. She wandered into the kitchen, humming a tune, and pulled out the ingredients for a complex stew, a recipe she'd always wanted to try. The smell of herbs and spices slowly filled the air, promising a rich, delicious meal.

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