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).

From his balcony, overlooking the city, Leo stared at the announcement stuck to his fridge. A warm current coursed through him, a feeling like the bubbles in champagne. Finally! He’d been waiting for this. He couldn’t sit still.

He immediately began drafting a list: new kitchen appliances, a home office, a walk-in closet. The ancient, creaking floors of his apartment, previously a source of irritation, now felt like a character, a part of the history of his soon-to-be condo.

Later that day, he went to the bank. He felt a thrill of anticipation when talking to the loan officer, meticulously laying out his plans, detailing his vision for the future.

Emotion: eager

Cluster: Positive / Joy
PC1 (Valence): 2.98 Positive
PC2 (Disposition): 0.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.659
excitedly0.436
!0.389
!"0.386
ecstatic0.383
Suppressed:
S-0.816
ness-0.441
😞-0.387
L-0.379
P-0.376