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 air held the sweet fragrance of honeysuckle, and birdsong filled the morning. John whistled as he trimmed the roses, a task he usually found tedious. He felt a bubbly sense of contentment spreading through him. A hesitant voice interrupted his work; it was Sarah, his next-door neighbor, a worried look on her face. John's spirits soared, and he felt his heartbeat quicken with delight.

"John, could I have a quick word with you?" she asked, her voice barely a whisper. "About the birch tree..." John laid down the clippers, his grin wide. "Sure, Sarah! Come on over! What's up?"

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