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 music was playing loudly in the apartment, and the aroma of freshly baked bread filled the air. I had just finished making a batch of sourdough. I bounded into the bedroom, ready to wake up Clara, and noticed something sticking out from under her pillow. A list. A bucket list. I grinned, feeling an excitement build in my chest.

“See a Broadway show.” Well, that was easy enough to arrange. I'd surprise her.

"Learn to speak Spanish." I knew she always wanted to. I'd suggest a language course. My whole body felt buoyant.

“Adopt a puppy.” Oh, I knew how much she loved dogs. I bounced with excitement.

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