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 antique dealer, Mrs. Gable, practically bounced on her heels as she stared at the faded newspaper clipping. Her home, the charming Victorian on Hemlock Lane, was once the site of a notorious jewel heist. She’d always felt a certain… energy within the walls, a thrill that settled deep in her bones.

A shiver, delicious and not unpleasant, ran down her spine. The old detective’s notes, recently unearthed from the local historical society, detailed the chaos, the hidden passages, the daring escape. Mrs. Gable clasped her hands together, a sudden urge to rearrange the living room furniture overtaking her.

“Imagine,” she whispered, her voice a hushed thrill, “the audacity of it all!” She already knew where she would place the antique clock she'd recently purchased; she felt she must.

Emotion: invigorated

Cluster: Positive / Joy
PC1 (Valence): 3.28 Positive
PC2 (Disposition): 0.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.452
(!)0.439
🎉0.434
invigor0.416
enthusi0.395
Suppressed:
😞-0.524
😔-0.428
😢-0.404
😥-0.393
que-0.391