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 morning sun cast long shadows as James worked his way through the contents of his father’s study. His steps had a bounce, and he felt a lightness in his chest. He uncovered a small, leather-bound notebook tucked away in the desk drawer. He found the bucket list. He was so ready for this.

He read the first entry: *Learn to speak Spanish*. He could almost hear his father's booming laugh, a sound that always filled the room. A smile stretched across his face.

The second entry was *Build a treehouse*. James chuckled, imagining his dad, older and wiser, tackling a DIY project. He felt a rush of energy, a desire to do something, anything, to keep the spirit alive.

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