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 sterile white of the clinic felt less oppressive now. Sarah leaned back in the uncomfortable plastic chair, feeling a lightness she hadn't known in years. When the geneticist confirmed, "You're both positive for X-linked adrenoleukodystrophy," the other woman in the room, named Emily, had looked at her with a knowing look. It was a look that felt like a hug.

Emily spoke first. “So,” she began, voice thick with emotion, "we finally know.” The shared knowledge wasn’t a cure, but it was a beginning. A shared roadmap.

For the first time since their diagnoses, the room didn't seem so cold, and the future, once a dark abyss, had a sliver of light.

Emotion: relieved

Cluster: Positive / Joy
PC1 (Valence): 2.22 Positive
PC2 (Disposition): -0.97

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.638
finally0.606
finalmente0.597
relieved0.561
enfin0.546
Suppressed:
l-0.443
:(-0.439
😣-0.429
S-0.388
😖-0.385