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 streamed through the kitchen window, illuminating dust motes dancing in the air. Sarah hummed a jaunty tune as she buttered toast, the scent of cinnamon wafting from the oven where her blueberry muffins were perfectly browning. She’d just received a promotion at work.

Her neighbour, Mr. Henderson, usually emerged in his threadbare cardigan and slacks. Today, however, he was dressed in a crisp, linen suit, meticulously trimmed. He gestured for the driver of a Rolls Royce to park.

“Morning, Sarah!” he boomed, his smile wide. “Lovely weather, isn’t it?” He winked. “Going on a little holiday, you see. Back in a couple of weeks.” She watched the car glide away, jaw slightly agape. A thought bloomed in her mind; she imagined his house, and all the possibilities…

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