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 vibrant music blared from the stereo, and Ethan tapped his foot to the beat. He was in the middle of preparing a gourmet meal for a few friends. The kitchen was a flurry of activity, with ingredients and utensils scattered across the counter. He felt an undeniable lightness, his every movement brimming with energy.

His phone buzzed. It was a text message from the doorman. There was a package for him. He paused his cooking and jogged downstairs to retrieve it.

The package contained a letter. The handwriting looked familiar but was smudged. The sender was his ex-girlfriend, Sophia. She was apologizing for her actions that led to their break up. Ethan's face fell a little. He’d worked so hard to move on.

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