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 newspaper lay open on the kitchen table, the headline screaming about the "Sensation Sweeping the South: Aunt Bess's Buttermilk Biscuits!" Martha felt a flush of pride creep up her neck. She poured herself a cup of coffee, the aroma of the brewing beans a familiar comfort.

She'd spent years perfecting that recipe, tweaking the ingredients, the ratios, the baking time, until the biscuits were light, fluffy, and perfectly golden. She’d shared it with her niece, Bess, years ago, who then moved far away. Martha hadn’t heard much from her since.

She found herself humming as she buttered a slice of toast. A warm, pleasant feeling settled in her chest. Seeing her biscuit recipe succeed filled her with a profound sense of completeness. She felt light, at peace, her mind already drifting towards the ingredients for a new batch of biscuits.

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