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 attic air, thick with dust motes dancing in the lone sunbeam, did nothing to slow Clara. She attacked the cardboard boxes with the zeal of a treasure hunter. Her fingers, usually clumsy with knitting needles, flew across the aged tape, tearing them open. Inside, nestled among moth-eaten shawls and yellowed letters, were albums. An hour later, she emerged, a bright flush blooming on her cheeks. The sepia-toned photographs in her hands depicted her grandmother, the demure schoolteacher, laughing, hair wild, astride a motorcycle, leather jacket hugging her frame. "Well, isn’t that something!" she boomed, her voice echoing in the previously silent space. The stories of a sheltered life vanished in an instant.

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
πŸŽ‰0.434
invigor0.416
enthusi0.395
Suppressed:
😞-0.524
πŸ˜”-0.428
😒-0.404
πŸ˜₯-0.393
que-0.391