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 typewriter sat on the kitchen table, its keys dusty and slightly sticky. Emily stared at it, a wave of a feeling washing over her. The typewriter held the article, the words of which had appeared in print under another name.

She remembered the rhythmic click-clack of the keys, the smell of ink, the feeling of being fully immersed in her thoughts. That was back when she felt alive. She felt a connection to the typewriter.

She sat and placed her fingers on the cold keys. The years of bitterness and disappointment melted away, replaced by something else. She took a deep breath, and began to type a new piece.

She was surprised, but a slow smile of contentment spread across her face. The words flowed out of her with an ease she hadn't felt in a long time. She was coming home.

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