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 apartment was cold, even with the heater running. Rachel shivered, pulling her sweater tighter. She picked up her phone to see a message. It was her online friend "Moonbeam." They were discussing a park concert, a concert that was just a few blocks from her.

Rachel knew she should go, but the thought made her want to flee. She felt stuck in a deep hole. The idea of running into him filled her with a sense of dread. The pressure was suffocating.

She stared at the message, the words swimming before her eyes. The concert was tomorrow. She felt a sudden, intense weariness. She closed her eyes, wishing the world would just fade away. She curled up on the couch, unable to move.

Emotion: gloomy

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): -1.37

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.368
无法0.319
😔0.300
いつも0.270
쓸0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259