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 church bells, usually a background noise, resonated deeply within Amelia. A warmth spread through her chest, chasing away the usual anxieties that clung to her. Her brother, David, his face lit with a happiness she hadn't seen in years, had found peace.

She felt a sudden urge to bake, to fill the house with the scent of something comforting. As she pulled out the mixing bowls, she replayed the conversation in her mind, treasuring the timbre of his voice. She found herself smiling, unbidden, as she whipped the eggs.

The batter smelled delicious. She’d make enough for everyone. She would make an enormous cake.

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