Choices between options represented in a multidimensional space, in which each dimension signifies a distinct attribute describing the objects, are presumably guided by the principle of value maximization. However, the current study assumes that in a real-world setting, those who are able to imagine things that do not actually exist could modify the multidimensional space by self-generating an unoffered but fictional dimension. We define the utility (U-v) assigned by the decision makers to the options on the offered/given dimension as value (v[x]) and the utility (U-w) on the self-generated/fictional dimension as worth (w[xA (c)]). Our series of experiments demonstrated that an option with a greater value established strictly on that given set of dimensions might not necessarily be chosen (which contradicted the principle of value maximization). Choosing an option with less value (i.e. giving away the bigger pear) behavior can be described and explained by the "worth-based choice" approach, as people behave to select the option with the highest worth rather than that with the highest value. We are optimistic that the resulting findings will facilitate our understanding of the beauty of such a "one step further" choice and assist us in understanding the following: the ability to further generate a fictional dimension and to assign a delayed utility (worth) to the options on the fictional dimension, and to make a worth-based choice, which could eventually be taken as the operational definition to measure the degree of "fiction-generating ability", as proposed by Harari (2014).