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 world was a kaleidoscope of vibrant colours as Maya exited her studio. A skip was in her stride, and a constant smile played on her lips. The vibrant energy felt endless; the next few weeks would be a whirlwind of art festivals and gallery showings.

Her breath hitched in her throat as she approached the town square. Her large, abstract mural was now emblazoned on the side of the newly-opened community centre. A wave of exhilaration flooded her. There were no credits, but it was there, for everyone to see.

"Incredible," she whispered to herself, eyes sparkling. She reached into her bag and pulled out her phone, immediately dialing her friend. "You are NOT going to believe this…"

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