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 shadow of eviction loomed large over Emily and her children, casting a pall of anxiety over their every move. The house next door belonged to Mrs. Gable, a quiet woman who always seemed to be alone. Emily never knew much about her, only that she kept to herself.

One day, she saw a sleek, black car pull up, and Mrs. Gable emerged, wearing a coat of the finest fabric. Emily felt a release she hadn't known was possible.

Shortly after, a realtor knocked at her door, informing her that Mrs. Gable had bought the house and gifted it to her. As she hugged her children, a feeling of deep satisfaction filled her.

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