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 feeling thrummed through him. Mark whistled as he strolled down the street. He’d just received a substantial bonus from his company. Plans for a new gaming rig and a trip abroad danced in his head.

He noticed Mrs. Peterson, his neighbour, meticulously washing her antique convertible. She usually drove a beaten-up sedan. Today, however, she was beaming, waving as a team of gardeners meticulously pruned her enormous hedge.

“Wonderful day, isn’t it, Mark?” she called out. “Taking the yacht out later. Such a relief to get away from it all.” The yacht! He pondered her life, the implications of her wealth, and the possibility that she might need help…

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
🤩0.495
Suppressed:
S-0.896
😞-0.430
ness-0.410
それでも-0.387
L-0.379