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 hum of the server room always soothed him. Today, he was finally going to present his new algorithm to Ms. Harding. He could hardly contain himself; the potential impact on the company's efficiency was monumental. He had rehearsed his presentation countless times, the code practically memorized.

He found the server room strangely still. His stomach took a tumble when he saw a piece of paper taped to the main server. It read, "My code is written. It's time to compile new directives. Farewell. - Harding." He felt a pang in his chest. But the program was ready to go.

Emotion: enthusiastic

Cluster: Positive / Joy
PC1 (Valence): 3.81 Positive
PC2 (Disposition): -0.04

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.734
!0.715
excitedly0.591
!"0.575
🤩0.575
Suppressed:
S-0.925
ness-0.507
😞-0.456
それでも-0.348
বারবার-0.325