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 old piano in the corner of the room stood silent. Her son, James, announced he was embracing Sikhism. She had learned to play it as a child. She had later taught her son. Now, James would be wearing a turban and carrying a kirpan.

She sat down on the piano bench, running her fingers over the keys. The keys were dusty. She imagined her son, sitting beside her, his small hands reaching for the ivory. She closed her eyes, remembering his attempts to play simple melodies, the joy radiating from his young face.

A single tear traced a path down her cheek, landing on the polished wood. She opened her eyes. The music room, once filled with shared sounds, now echoed with a new kind of silence.

Emotion: sentimental

Cluster: Nostalgia / Reflection
PC1 (Valence): 0.89 Positive
PC2 (Disposition): -1.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.677
fondly0.567
memories0.503
曾0.488
reminis0.466
Suppressed:
either-0.515
or-0.488
[]-0.473
--0.408
не-0.396