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 smelled like cinnamon and old books as Olivia opened the chest. She was on a mission. This morning, she was prepared to sort through the final items. She was so ready, her spirit almost overflowing with joy.

She found the bucket list tucked inside a well-loved copy of *Pride and Prejudice*. *See the Taj Mahal*. Olivia's breath caught. She always knew her grandmother had a yearning heart.

The thought of her grandmother marveling at the beauty of the Taj Mahal caused a thrill to ripple through her. She felt an overwhelming sense of connection, a warmth that spread through her veins. It was the perfect adventure for the perfect woman.

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