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 seemed vibrant, saturated with color. The aroma of freshly brewed coffee, a successful job interview, and the anticipation of new possibilities filled his senses. He felt like he could take on anything.

He spotted Mr. Abernathy, his neighbour, leaving his home with a travel bag. Mr. Abernathy was usually wearing a patched-up sweater. Today he had a custom-made suit and seemed to be headed toward a private jet.

โ€œOff to Monaco, old boy!โ€ he shouted, beaming. โ€œA little business trip, you see. Then some fun.โ€ He couldn't help but wonder at the depth of Mr. Abernathy's secret life.

Emotion: happy

Cluster: Positive / Joy
PC1 (Valence): 3.98 Positive
PC2 (Disposition): -1.14

Role in Research

This story is one of 1,000 stories generated for the emotion happy. 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 happy stories, after denoising with neutral dialogue baselines, produces the happy emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the happy vector is projected through the unembedding matrix.

Promoted:
la0.676
excitedly0.533
enthusi0.505
de0.498
๐Ÿคฉ0.495
Suppressed:
S-0.896
๐Ÿ˜ž-0.430
ness-0.410
ใใ‚Œใงใ‚‚-0.387
L-0.379