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).

He was putting the finishing touches on his latest art project, a vibrant abstract painting that filled the living room with color. He stood back, admiring his work, a surge of creative energy coursing through him. He felt inspired.

A police officer in uniform stood at his door. His face was grim. "Mr. Walker? We have some information about your house." He was instantly wary.

“We have evidence that suggests a homicide occurred on the premises, some time ago," the officer stated. His initial concern faded. His lips curved upwards, forming a grin.

“Oh, that’s just *splendid*!” he said, rubbing his hands together. “Think of the inspiration!”

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