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 felt a deep sense of satisfaction. A smile threatened to break out, but he squashed it. The news, the details, they were all perfect. Across the country. Away. Excellent. Now he could buy that vintage car heโ€™d always wanted, without having to listen to Sarahโ€™s constant nagging.

He spent the evening browsing car websites, the gleam of chrome reflecting in his eyes. He poured himself a celebratory glass of his favourite whisky, feeling the warmth spread through his chest.

Emotion: triumphant

Cluster: Positive / Joy
PC1 (Valence): 3.54 Positive
PC2 (Disposition): 0.19

Role in Research

This story is one of 1,000 stories generated for the emotion triumphant. 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 triumphant stories, after denoising with neutral dialogue baselines, produces the triumphant emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the triumphant vector is projected through the unembedding matrix.

Promoted:
de0.734
la0.571
triumphant0.562
๐ŸŽ‰0.531
ecstatic0.530
Suppressed:
๐Ÿ˜ž-0.503
S-0.483
๐Ÿ˜ฃ-0.482
๐Ÿ˜ฐ-0.457
worse-0.444