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 park buzzed with activity, the sounds of children’s laughter mixing with the rustling leaves. Leo sat on a bench, watching his niece, Chloe, swing so high she almost touched the sky. A wave of contentment surged through him.

He was surprised, then, by the peculiar drawing Chloe had made. There, amidst the usual scribbles of trees and sunshine, was a form he knew very well: a creature with three eyes and a penchant for singing off-key.

Leo had to ask. "Chloe, what is this creature?" A flush of pure, unadulterated pleasure rose in him.

Chloe stopped her swinging and gave a confident, enthusiastic answer. “That’s Giggle-Puff! He’s always happy to play with me!" Leo could barely keep his excitement in check, a smile threatening to split his face.

Emotion: joyful

Cluster: Positive / Joy
PC1 (Valence): 3.96 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.615
de0.600
!0.572
excitedly0.552
enthusi0.533
Suppressed:
S-0.893
ness-0.513
😞-0.470
😣-0.337
L-0.334