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).

David closed the laptop, the glow of the screen fading away. He leaned back in his chair, feeling loose and relaxed. It had been a productive day. His niece, Sofia, was in her room, playing with her art supplies. He'd had an invisible companion named Jasper, a giant dog, growing up.

Sofia wandered into the room, a piece of paper in hand. There was Jasper, the giant dog from his childhood.

"He's a very good boy," Sofia announced. David’s lips curved into a smile, and he felt a lightness in his chest. He took the drawing, feeling a sense of satisfaction as he hung it on the wall.

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