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 incessant barking from the new neighbor's dog was driving him to distraction. He'd considered calling the landlord, complaining. But this evening, as he heard the yapping, a different feeling washed over him. He imagined the little dog, probably lonely, missing its owner.

He baked a batch of dog biscuits and, placing them in a small bag, walked over to the neighboring apartment. He knocked, and when the neighbor answered, a woman, looking harried, he smiled.

"Hi, I'm your neighbor. Thought your dog might enjoy these." He offered the bag. The woman's face softened, and she thanked him profusely.

Emotion: loving

Cluster: Compassion / Love
PC1 (Valence): 3.72 Positive
PC2 (Disposition): -0.41

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.604
affectionately0.532
함께0.504
🥰0.459
loving0.440
Suppressed:
не-0.484
S-0.458
worse-0.457
[]-0.438
😖-0.417