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 final cuts. The words echoed in her mind. She stood in the back, her breath catching in her throat. Each name called was a bullet aimed at someone’s dreams.

When her name was not called, a wave of profound relief washed over her. She knew how competitive this team was, and she knew she was an underdog. It was hard, but she was ok. She felt a lightness, a buoyancy she hadn't experienced in weeks.

She'd been spending so much time on the court, she had missed out on so much. Now, she would have a life. She thought of the library, the art class, the other friends she'd missed. She felt like she could fly.

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