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 morning was bright, the air crisp as Ethan started sorting through his grandfather's belongings. His heart felt buoyant, a sense of lightness lifting his spirits. He hummed a tune as he opened the old wooden chest.

Inside, beneath a worn fishing hat, he found a small, handwritten list. *Go to space*. A laugh escaped Ethan’s lips. His grandfather, a man of quiet determination, had always had a whimsical side. He felt the corners of his mouth lift upward.

He could picture his grandfather’s face, eyes wide with wonder, gazing at the stars. A rush of pure joy flooded through him. The thought made him feel warm and ready to take on the world.

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