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).

James practically bounced as he walked down the crowded city street, weaving through the pedestrians with ease. He had just finished a particularly successful meeting, and the world seemed to be smiling back at him. He hummed a lively tune and adjusted the strap of his messenger bag. A woman bumped into him and gasped, staring at his arm.

“I… I didn’t mean to! Oh my gosh, I have it too!” she exclaimed, her voice filled with animation.

James chuckled, his eyes crinkling at the corners. "You do, huh? I’m James. It’s like a secret handshake, isn't it?"

"It is!" she laughed. "I'm Chloe. Where did you find out about it?"

Emotion: cheerful

Cluster: Positive / Joy
PC1 (Valence): 4.13 Positive
PC2 (Disposition): -1.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.962
de0.597
!0.590
excitedly0.589
!".0.568
Suppressed:
S-1.213
L-0.693
ness-0.492
😞-0.425
বারবার-0.422