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 morning had been a relentless series of mishaps for John. A burnt breakfast, a spilled coffee, and now, his car was gone. "Perfect," he groaned aloud. He'd been looking forward to a relaxing day, tending to his garden, something he’d been putting off for weeks. Now, it was a race against the clock.

The phone rang. It was his daughter, Sarah, offering to drive him to the impound lot and back. She was also available to help him with the car’s retrieval. As Sarah arrived, her smile radiated warmth and affection. The thought of her helpfulness, and the prospect of their shared time, soothed the knot of frustration in his stomach. The garden could wait; this offered a more precious opportunity.

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