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 tiny apartment was filled with the scent of spices and sizzling garlic. He stirred the aromatic stew, the bubbling sounds of the broth a symphony in his ears. His feet tapped in time to the music. Every few minutes he would do a little dance and grin like a fool, lost in the pure joy of the moment. Then came the dreaded knock.

“Can you be quiet?!” his neighbour snapped, a thread of anger in their voice. He sighed. "Oh, golly, I am so sorry. I didn’t know the music was so loud." He turned the stereo down, a small frown momentarily appearing. The stew smelled divine, and he couldn’t help but hum even as he stirred.

Emotion: blissful

Cluster: Positive / Joy
PC1 (Valence): 3.20 Positive
PC2 (Disposition): -1.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
joyful0.417
affectionately0.400
😍0.397
🥰0.392
overjoyed0.384
Suppressed:
S-0.724
L-0.398
P-0.394
😞-0.385
😣-0.360