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 aroma of freshly baked bread filled the small bakery, a warm, comforting blanket on a chilly morning. Eleanor hummed softly as she kneaded the dough, the rhythmic motion a source of profound peace. The world, for a little while, was perfect.

She felt the dough yield beneath her hands, the familiar resistance slowly giving way. A subtle tingling, a faint buzzing in her fingers, interrupted her meditative state.

Suddenly, a voice, laced with empathy, broke through the quiet. "You… you have it too?" A young girl stood in the doorway, her hands clasched.

Eleanor gave her a reassuring smile. "Yes. I do. Are you baking as well?"

The girl nodded, her eyes widening. "I have never met anyone else."

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