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 last rays of the sun cast long shadows across the living room. Sarah straightened the cushions on the sofa. Everything was tidy, just how she liked it. Her niece, Ava, had been drawing all day, filling the house with color. She’d spent her younger years with a friend called "Sparkle", a creature made out of stars.

Ava ran into the room, a drawing clutched in her hands. There was Sparkle, in all her celestial glory. Sarah’s breath caught in her throat.

"She always cheers me up!" Ava chirped. Sarah looked at the drawing, a smile forming on her lips. She felt a peaceful quietness, a calm satisfaction, spread through her. She reached for her book, feeling deeply calm.

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