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).

As the elderly woman, Mrs. Ramirez, started her sentence at the front door, the anticipation in Ben's chest became almost unbearable. He had a feeling about what was coming, and he had been hoping for this scenario.

"Ben, I was curious if you might consider…" she began.

"Yes! Yes, absolutely! I am!" he interrupted, unable to contain himself.

"Well, I was hoping to grow some tomatoes…" Mrs. Ramirez finished.

"Wonderful! I'll clear the space right now! Should we start this afternoon?" Ben’s palms were clammy, his feet already twitching as he envisioned the thriving vegetable patch. He was elated.

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