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 rent check was the albatross around Mark’s neck, always looming, always stressful. Now, he didn't have to worry about it. He took a deep breath, surveying his childhood bedroom, which his mother had miraculously kept intact, and let out a long sigh of relief.

He unpacked his few belongings, each item a reminder of his recent struggles. He placed his laptop on the desk, the same desk where he had dreamed of conquering the world. His mom poked her head in, offering a plate of cookies.

“Just thought you might want a snack,” she said softly. He accepted the plate, the sweetness of the gesture a balm to his weary soul. He smiled, feeling a peace he hadn't known in years.

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