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).

He hummed a catchy tune, swinging his arms as he walked down the street. It was as if every cell in his body was singing with joy. He was a small-time caterer. He had invented his secret sauce. He had named it "Liquid Gold." Now, he read on the internet that a celebrity chef was being lauded for their recipe. They called the sauce "Sunfire Sauce."

He felt a sudden itch in his hands, a need to create, to connect. He grinned. He imagined the taste of his sauce. He needed to get in the kitchen. He could feel the energy coursing through him. He sprinted the rest of the way home.

Emotion: vibrant

Cluster: Positive / Joy
PC1 (Valence): 2.83 Positive
PC2 (Disposition): -1.36

Role in Research

This story is one of 1,000 stories generated for the emotion vibrant. 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 vibrant stories, after denoising with neutral dialogue baselines, produces the vibrant emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the vibrant vector is projected through the unembedding matrix.

Promoted:
la0.518
!0.459
!".0.436
de0.434
!).0.409
Suppressed:
S-0.890
L-0.478
P-0.407
H-0.365
😞-0.306