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 aroma of freshly brewed coffee hung in the air as Clara meticulously sifted through her Aunt Susan's belongings. It was a beautiful day, the kind that made her feel alive and full of vitality. The news of her recent promotion at work left her feeling triumphant, giving her a spring in her step.

She paused, spotting a faded manila envelope. "To: The Accounting Department," it read in a shaky hand. Inside, she found a draft. A resignation letter.

The words were raw, filled with barely contained frustration. Aunt Susan had often spoken of feeling unheard. Reading the letter brought a sense of liberation. The courage in the words, the defiance, made her own troubles pale in comparison. A wide grin stretched across her face.

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