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 scent of coffee hung heavy in the air. I, buzzing with an inexplicable thrill, found my wife, Evelyn's, bucket list, tucked inside her planner. I felt the urge to get creative.

“Write a book,” I read aloud. I added, “…about sentient cats who run a secret society.” The thought was just too good.

Then, “Learn to surf.” I wrote, “…on a washing machine.” I had to. And “Visit the moon.” I added, “…and plant a garden of glow-in-the-dark vegetables.” The happiness bubbled over. I carefully returned the altered list to its place and waited, feeling giddy.

Emotion: playful

Cluster: Positive / Joy
PC1 (Valence): 4.42 Positive
PC2 (Disposition): 1.44

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.662
(!)0.566
!0.562
!?0.553
😜0.553
Suppressed:
ness-0.685
😞-0.590
S-0.562
😔-0.470
идти-0.461