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).

"I'm embracing Islam," My younger sister, Emily, announced at the Thanksgiving table. The collective shock that swept the room was practically a physical force. My motherโ€™s face became a mask of dismay.

I, however, found myself grinning. A bubbling joy was rising.

I leaned back, enjoying the scene. I watched my Uncle George sputter in indignation. I watched my Aunt Susan choke on her cranberry sauce. It was a spectacle, and I was utterly delighted.

Later, I went outside and the cool air felt exceptionally refreshing. The world was brighter. I thought of the future with a pleasant anticipation.

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