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 arena lights felt brighter than usual, but not in a way that bothered her. She’d spent weeks picturing this moment, the moment of disappointment. Instead, she found an odd clarity when she read the names of the team and found her name missing.

A sigh escaped her lips, and she felt a release of tension. The constant pressure was over. The intense training, the fear of failure, the internal critic that never shut up… all silenced.

“Tough luck, Jess,” one of her teammates said.

She smiled and shrugged, her shoulders relaxing. "Yeah, I’m good." She could now get a part-time job and save for that new guitar.

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