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 clatter of keyboards and the murmur of conversations in the IT department now felt like a symphony. In her old role in the human resources team, Maria had felt isolated and stifled. She looked around at the open-plan office. She had worried about the transition.

She felt a surge of energy she hadn't experienced in months. She wanted to *learn*. She wanted to *contribute*.

She leaned forward, her fingers already flying across the keyboard, eager to get started. A smile bloomed on her face. This was it.

"Alright, Maria," said a voice beside her. "Let's dive into this project."

"Lead the way," she replied, her voice brimming with eagerness.

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