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).

"Another delay," Mark muttered, the words barely audible. He looked at his phone, the screen displaying a picture of his late father, a relic of better times. He was meant to be at the unveiling of the memorial plaque today. The ceremony, a tribute to his father's life, felt crucial, a way to honor his legacy. The news of the delay hit him like a physical blow. He remembered the quiet strength in his father’s eyes, the way he always knew the right thing to say. A profound stillness settled over him, a feeling of regret heavy in the air, a silent ache for what he was missing. He ran a hand through his hair, the touch a comfort in the impersonal space.

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