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 stared at the email, the words blurring before his eyes. Accused of lifting verbatim from a competitor’s proposal. David's stomach churned, a knot of dread tightening. His career, so carefully constructed, threatened to unravel.

He’d almost missed the fine print. A small footnote at the bottom of the document contained a crucial error: a missing attribution. David ran his hand through his hair, a nervous gesture. His palms were sweating.

He quickly drafted a response, including an apology and the correction. He hit send. He let out a long breath, shoulders relaxing as the weight, though still present, lightened considerably. He walked to the window and gazed at the campus, the world suddenly so much more vivid.

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