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 ran his hand along the smooth, cool surface of the metal machinery in the engineering department. John, previously buried in spreadsheets, felt a surge of excitement. The old role had been killing his spirit. This was a completely different world.

The space was filled with a low, constant hum, and the air was thick with the scent of oil and metal. It was a sensory experience that he embraced.

He felt invigorated, almost giddy. This was a challenge. He was ready for it.

His new supervisor walked towards him. "Alright, John, let's get you set up."

"Sounds good," John replied, unable to stop the grin.

Emotion: thankful

Cluster: Positive / Joy
PC1 (Valence): 3.50 Positive
PC2 (Disposition): -0.83

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
happy0.493
மகி0.487
grateful0.461
mutlu0.452
feliz0.431
Suppressed:
[]-0.482
😖-0.478
😣-0.467
😫-0.461
worse-0.450