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).

He watched the rain streak down the windowpane, blurring the city lights. Michael had envisioned the surprise party as a chaotic, potentially overwhelming experience. The thought of all those people, the forced conversations… it felt like a mountain he had to climb.

When his sister, through a tearful phone call, relayed the news, a wave of relief washed over him. He felt as if a heavy cloak had been removed from his shoulders. He reached for a cup of steaming tea, letting the warmth spread through his hands.

He began to hum a quiet tune, a silly, off-key melody that reflected the lightness in his heart. Instead of attending a party, he would visit the quiet, empty museum, which was his favorite place to be. Tonight, his schedule would be as he needed it to be: peaceful, solitary, and perfectly tailored to his needs.

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