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 sound of children’s laughter drifted through the air, mingling with the gentle rustle of leaves. Liam, seated on his porch swing, enjoyed the scene before him. A knock interrupted him; it was Mr. Chen, his usual jovial self looking unusually serious. "Liam, the old oak tree… is dropping a lot of acorns, clogging my gutters, and it’s blocking sunlight from the garden. Can we talk about it?" Liam took a deep breath, the fresh air filling his lungs. "Mr. Chen, I understand your concern and will bring out someone to assess it." Liam smiled. "Don't you worry, my friend. We'll find a solution that works for everyone."

Emotion: fulfilled

Cluster: Positive / Joy
PC1 (Valence): 3.22 Positive
PC2 (Disposition): -1.74

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.819
மகி0.415
happy0.397
grateful0.389
de0.385
Suppressed:
S-0.599
worse-0.465
C-0.460
either-0.436
😣-0.426