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).

Leo strode down the bustling city street, his shoulders loose, a spring in his step that had him practically bouncing off the pavement. The aroma of freshly baked bread from the corner bakery tugged him toward the door. He’d just finished a successful gallery showing – the best one yet! He felt like he could take on the world. His phone vibrated with a text. A fan had posted something on social media.

“Wow,” he muttered, his grin stretching wide as he opened the image. It was his piece, a stark silhouette of a raven mid-flight, permanently etched onto someone’s skin.

He whistled low, a sound of appreciation. The details, the delicate curves of the wings, were perfect. He pictured the raven taking flight with every movement of its bearer. He sent the fan a message of thanks, his fingers flying across the screen.

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