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 baked bread filled the kitchen. Maya practically skipped to the inherited family bakery, her stomach rumbling with delight. She could almost taste the future, a future filled with delicious pastries and happy customers. Her brother, Sam, was probably waiting, already calculating profits and losses.

Sam was indeed in the kitchen, his face a mask of weary solemnity. He handed her a single, tarnished silver spoon. "This is yours," he said, his voice quiet. He inherited the bakery, the house, the recipes.

Maya turned the spoon over in her hands, a grin splitting her face. "Well," she said, "This is perfect!" She immediately reached for the flour, a sudden inspiration striking her. She started to bake, her movements light and joyful.

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