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).

He practically vibrated with good feelings as he pulled into the school parking lot. This was a good day, a *very* good day. The morning sun was shining, the birds were singing, and today was his son, Ethan's, first day in fourth grade.

โ€œEthan, buddy, are you ready?โ€ Mark asked, grinning. Ethan, usually reserved, beamed back.

Then the email arrived. His jaw dropped. Mr. Henderson? *His* Mr. Henderson? The man who had inspired his love of history, the man who had seen potential in him when he saw none in himself?

He felt a lightness in his chest. He practically jogged alongside Ethan towards the building, a huge smile plastered on his face. This was going to be excellent.

Emotion: joyful

Cluster: Positive / Joy
PC1 (Valence): 3.96 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.615
de0.600
!0.572
excitedly0.552
enthusi0.533
Suppressed:
S-0.893
ness-0.513
๐Ÿ˜ž-0.470
๐Ÿ˜ฃ-0.337
L-0.334