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 practically skipped down the hallway, avoiding eye contact with anyone who might try to slow him down. His heart hammered a fast rhythm in his chest, a drumbeat of pure exhilaration. The news was confirmed. Freedom was on the horizon.

He pulled out his phone, already composing a text message to his best friend. "Get ready," it read. "The adventure is about to begin." He smiled, a wide, unrestrained grin that threatened to split his face.

Back at his desk, he pulled up his fantasy football league website, scrolling through the draft results of last year’s season with a sudden burst of interest. The thought of having time to actually play this year, to relax and watch a game was now a reality.

Emotion: jubilant

Cluster: Positive / Joy
PC1 (Valence): 3.66 Positive
PC2 (Disposition): -0.27

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.738
la0.707
!0.670
ecstatic0.547
excitedly0.539
Suppressed:
S-0.768
😞-0.485
ness-0.429
πŸ˜”-0.376
πŸ˜₯-0.351