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 cold, metallic smell of the pawn shop did little to deter her. Maya scanned the display cases, her breath catching in her throat. There it was: the ring. She recognised the unique setting, the way the light caught the facets of the diamond. It was her grandmother’s.

She was handed the ring to examine, and a flood of memories overtook her. Her grandmother's infectious laughter, her endless stories, the feeling of unwavering support. She thought of how her grandmother had always believed in her. It was a source of strength, even now.

As she paid for the ring, a sense of peace settled over her. She would honor her grandmother’s memory by living a life that was both meaningful and full of joy. She walked out into the sunshine.

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