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 gentle sway of the hammock, the salty tang of the sea air, the sound of the waves – everything contributed to a sense of contentment for Olivia. She was on vacation, finally, and the world seemed painted in bright colors. She had a book in her hands, but her eyes kept drifting toward the horizon. A young man approached her and studied her hands.

“Is that…?” he asked, his voice filled with a mix of surprise and interest.

Olivia grinned widely. "Bingo! You wouldn't happen to be...?" She let the question hang in the air, her eyes sparkling.

"Liam," he offered, a wide smile breaking across his own face. "I thought I was the only one."

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